[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-gkiril--oie-resources":3,"tool-gkiril--oie-resources":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":81,"owner_email":82,"owner_twitter":83,"owner_website":84,"owner_url":85,"languages":84,"stars":86,"forks":87,"last_commit_at":88,"license":84,"difficulty_score":89,"env_os":90,"env_gpu":91,"env_ram":91,"env_deps":92,"category_tags":95,"github_topics":96,"view_count":117,"oss_zip_url":84,"oss_zip_packed_at":84,"status":16,"created_at":118,"updated_at":119,"faqs":120,"releases":121},997,"gkiril\u002Foie-resources","oie-resources","A curated list of Open Information Extraction (OIE) resources: papers, code, data, etc.","oie-resources 是一个精心整理的开源信息抽取（Open Information Extraction, OIE）资源列表，包含研究论文、代码、数据集以及相关应用等内容。它不仅聚焦于OIE系统本身，还涵盖了与OIE密切相关的领域，比如开放关系分类、下游应用场景等，为研究人员和开发者提供了全面的参考资料。\n\n在自然语言处理中，OIE 的目标是从非结构化文本中以无监督的方式提取未知的关系及其参数，通常以“主语-关系-宾语”的三元组形式呈现。例如，从句子“AMD是一家总部位于美国的技术公司”中，OIE 系统可以抽取出 (“AMD”; “总部位于”; “美国”) 和 (“AMD”; “是”; “技术公司”)。这种能力解决了从海量文本中自动获取结构化知识的难题，为构建知识图谱、问答系统、文本摘要等应用提供了基础支持。\n\noie-resources 非常适合从事自然语言处理的研究人员、开发者以及对信息抽取技术感兴趣的学者使用。它按照时间顺序和主题类别整理了大量高质量论文，并提供了多语言OIE系统的资源，涵盖中文、德语、西班牙语等多种语言。此外，列表中还包括代码实现、数据集、幻灯片和演示内","oie-resources 是一个精心整理的开源信息抽取（Open Information Extraction, OIE）资源列表，包含研究论文、代码、数据集以及相关应用等内容。它不仅聚焦于OIE系统本身，还涵盖了与OIE密切相关的领域，比如开放关系分类、下游应用场景等，为研究人员和开发者提供了全面的参考资料。\n\n在自然语言处理中，OIE 的目标是从非结构化文本中以无监督的方式提取未知的关系及其参数，通常以“主语-关系-宾语”的三元组形式呈现。例如，从句子“AMD是一家总部位于美国的技术公司”中，OIE 系统可以抽取出 (“AMD”; “总部位于”; “美国”) 和 (“AMD”; “是”; “技术公司”)。这种能力解决了从海量文本中自动获取结构化知识的难题，为构建知识图谱、问答系统、文本摘要等应用提供了基础支持。\n\noie-resources 非常适合从事自然语言处理的研究人员、开发者以及对信息抽取技术感兴趣的学者使用。它按照时间顺序和主题类别整理了大量高质量论文，并提供了多语言OIE系统的资源，涵盖中文、德语、西班牙语等多种语言。此外，列表中还包括代码实现、数据集、幻灯片和演示内容，极大地方便了用户快速上手和深入研究。\n\n独特亮点在于其全面性和条理性，无论是按年份追溯OIE的发展历程，还是根据具体应用场景查找相关工作，oie-resources 都能提供清晰的指引。对于希望探索信息抽取领域的用户来说，这是一个不可多得的知识宝库。","# Open Information Extraction (OIE) Resources\n\nA curated list of Open Information Extraction (OIE) resources: research papers, code, data, applications, etc. The list is not limited to Open Information Extraction systems exclusively. It also includes work highly related to OIE, such as taxonomizing open relations and using OIE in downstream applications. \n\n## Table of contents\n\n* [Introduction to OIE](#introduction-to-oie)\n* [Papers sorted in chronological order](#papers-sorted-in-chronological-order)\n  * [2006](#2006)\n  * [2007](#2007)\n  * [2008](#2008)\n  * [2009](#2009)\n  * [2010](#2010)\n  * [2011](#2011)\n  * [2012](#2012)\n  * [2013](#2013)\n  * [2014](#2014)\n  * [2015](#2015)\n  * [2016](#2016)\n  * [2017](#2017)\n  * [2018](#2018)\n  * [2019](#2019)\n  * [2020](#2020)\n  * [2021](#2021)\n  * [2022](#2022)\n* [Papers grouped by category](#papers-grouped-by-category)\n  * [Surveys](#surveys)\n  * [Evaluation](#evaluation)\n  * [OIE for downstream applications](#oie-for-downstream-applications)\n    * [Question Answering](#question-answering)\n    * [Slot Filling](#slot-filling)\n    * [Event Extraction](#event-extraction)\n    * [Text Summarization](#text-summarization)\n    * [Knowledge Base Population](#knowledge-base-population)\n    * [Knowledge Base Construction](#knowledge-base-construction)\n    * [Entity Linking](#entity-linking)\n    * [Relation Linking](#relation-linking)\n    * [Open Link Prediction](#open-link-prediction)\n    * [Relation Extraction](#relation-extraction)\n    * [Relating Entities](#relating-entities)\n    * [Story Comprehension](#story-comprehension)\n    * [Text Generation](#text-generation)\n    * [Video Grounding](#video-grounding)\n  * [OIE in Different Languages](#oie-in-different-languages)\n    * [OIE Systems for German Language](#oie-systems-for-german-language)\n    * [OIE Systems for Portugese Language](#oie-systems-for-portugese-language)\n    * [OIE Systems for Spanish Language](#oie-systems-for-spanish-language)\n    * [OIE Systems for Chinese Language](#oie-systems-for-chinese-language)\n    * [OIE Systems for Persian Language](#oie-systems-for-persian-language)\n    * [OIE Systems for Italian Language](#oie-systems-for-italian-language)\n    * [OIE Systems for Indonesian Language](#oie-systems-for-indonesian-language)\n    * [OIE Systems for Greek Language](#oie-systems-for-greek-language)\n  * [Supervised OIE](#supervised-oie)\n  * [Canonicalization of OIE](#canonicalization-of-oie)\n* [Slides](#slides)\n* [Talks](#talks)\n* [Code](#code)\n* [Data](#data)\n  * [OIE corpora](#oie-corpora)\n  * [Resources derived from OIE output](#resources-derived-from-oie-output)\n* [PhD theses](#phd-theses)\n* [Demos](#demos)\n\n## Introduction to OIE\n\nOpen Information Extraction (OIE) systems aim to extract unseen relations and their arguments from unstructured text in unsupervised manner. In its simplest form, given a natural language sentence, they extract information in the form of a triple, consisted of subject (S), relation (R) and object (O).\n\nSuppose we have the following input sentence:\n\n    AMD, which is based in U.S., is a technology company.\n\nAn OIE system aims to make the following extractions:\n\n    (\"AMD\"; \"is based in\"; \"U.S.\")\n    (\"AMD\"; \"is\"; \"technology company\")\n\n## Papers sorted in chronological order\n\n### 2006\n\n* *[\"Machine Reading\"](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FSymposia\u002FSpring\u002F2007\u002FSS-07-06\u002FSS07-06-001.pdf)* - AAAI 2006\n\n  Oren Etzioni, Michele Banko, Michael J. Cafarella\n\n### 2007\n* *[\"Open Information Extraction from the Web\"](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FIJCAI\u002F2007\u002FIJCAI07-429.pdf)* - IJCAI 2007\n  \n  Michele Banko,  Michael J. Cafarella, Stephen Soderland, Matthew Broadhead, Oren Etzioni\n  \n* *[\"Unsupervised Resolution of Objects and Relations on the Web\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fobject_identification_camera_ready_4.pdf)* - NAACL 2007\n\n  Alexander Yates, Oren Etzioni\n  \n* *[\"TextRunner: Open Information Extraction on the Web\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002Fp25-yates.pdf)* -  HLT-NAACL 2007\n\n  Alexander Yates, Michele Banko, Matthew Broadhead, Michael J. Cafarella, Oren Etzioni, Stephen Soderland\n  \n### 2008\n* *[\"The Tradeoffs between Open and Traditional Relation Extraction\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Facl08.pdf)* - ACL 2008\n\n  Michele Banko, Oren Etzioni\n\n* *[\"Open Knowledge Extraction through Compositional Language Processing\"](https:\u002F\u002Fwww.cs.rochester.edu\u002F~schubert\u002Fpapers\u002Fopen-knowledge-step08.pdf)* - STEP 2008\n\n  Benjamin Van Durme, Lenhart K. Schubert\n\n* *[\"Open Information Extraction from the Web\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=1409378)* - Commun. ACM 2008\n\n  Oren Etzioni, Michele Banko, Stephen Soderland, Daniel S. Weld\n  \n### 2009\n\n* *[\"Using Wikipedia to Bootstrap Open Information Extraction\"](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.143.4369&rep=rep1&type=pdf)* - SIGMOD 2009\n  \t\n    Daniel S. Weld, Raphael Hoffmann, Fei Wu\n    \n### 2010\n\n* *[\"Open Information Extraction Using Wikipedia\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP10-1013)* - ACL 2010\n\n  Fei Wu, Daniel S. Weld\n  \n* *[\"Identifying Functional Relations in Web Text\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Femnlp10.pdf)* - EMNLP 2010\n  \n  Thomas Lin, Mausam, Oren Etzioni\n\n* *[\"Adapting Open Information Extraction to Domain-Specific Relations\"](https:\u002F\u002Fwww.aaai.org\u002Fojs\u002Findex.php\u002Faimagazine\u002Farticle\u002Fview\u002F2305)* -  AI Magazine (31), 2010\n\n  Stephen Soderland, Brendan Roof, Bo Qin, Shi Xu, Mausam, Oren Etzioni \n  \n### 2011\n\n* *[\"Open Information Extraction: The Second Generation\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fetzioni-ijcai2011.pdf)* -  IJCAI 2011 ([slides](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fcourses\u002Fcol864\u002Fspring2017\u002Fslides\u002F03-openie.pdf))\n  \n  Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland, Mausam\n  \n* *[\"Identifying Relations for Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD11-1142)* - EMNLP 2011 [(resources (code, data)](http:\u002F\u002Freverb.cs.washington.edu\u002F))\n\n  Anthony Fader, Stephen Soderland, Oren Etzioni\n  \n* *[\"Filtering and Clustering Relations for Unsupervised Information Extraction in Open Domain\"](https:\u002F\u002Fperso.limsi.fr\u002Fbg\u002Ffichiers\u002F2011\u002Fcikm0874-wang.pdf)* - CIKM 2011\n\n  Wei Wang, Romaric Besançon, Olivier Ferret, Brigitte Grau\n\n* *[\"An Analysis of Open Information Extraction based on Semantic Role Labeling\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fkcap11.pdf)* - K-CAP 2011\n\n  Janara Christensen, Mausam, Stephen Soderland, Oren Etzioni\n\n### 2012\n\n* *[\"Open Language Learning for Information Extraction\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1048)* - EMNLP-CoNLL 2012 ([resources (code, data, binaries)](http:\u002F\u002Fknowitall.github.io\u002Follie\u002F))\n\n  Mausam, Michael Schmitz, Stephen Soderland, Robert Bart, Oren Etzioni\n  \n* *[\"PATTY: A Taxonomy of Relational Patterns with Semantic Types\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1104)* - EMNLP-CoNLL 2012\n\n  Ndapandula Nakashole, Gerhard Weikum, Fabian M. Suchanek\n  \n* *[\"Ensemble Semantics for Large-scale Unsupervised Relation Extraction\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1094)* - EMNLP-CoNLL 2012\n\n  Bonan Min, Shuming Shi, Ralph Grishman, Chin-Yew Lin\n  \n* *[\"WiSeNet: building a wikipedia-based semantic network with ontologized relations\"](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~moro\u002FMoroNavigli_CIKM12.pdf)* - CIKM 2012 ([resources](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F))\n\n  Andrea Moro, Roberto Navigli\n  \n* *[\"Open Information Extraction for SOV Language Based on Entity-Predicate Pair Detection\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC12-3038)* -  COLING 2012\n\n  Woong-Ki Lee, Yeon-Su Lee, Hyoung-Gyu Lee, Won-Ho Ryu, Hae-Chang Rim\n  \n* *[\"A Weighting Scheme for Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN12-2011)* - HLT-NAACL 2012\n\n  Yuval Merhav\n\n* *[\"Dependency-based open information extraction\"](http:\u002F\u002Fwww.anthology.aclweb.org\u002FW\u002FW12\u002FW12-0702.pdf)* - Joint Workshop on Unsupervised and Semi-Supervised Learning in NLP @ ACL 2012\n\n  Pablo Gamallo, Marcos Garcia\n  \n* *[\"KrakeN: N-ary Facts in Open Information Extraction\"](http:\u002F\u002Fwing.comp.nus.edu.sg\u002F~antho\u002FW\u002FW12\u002FW12-3010.pdf)* - AKBC-WEKEX@NAACL-HLT 2012\n\n  Alan Akbik, Alexander Löser\n  \n* *[\"Improving Open Information Extraction for Informal Web Documents with Ripple-Down Rules\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-642-32541-0_14)* - PKAW 2012\n\n  Myung Hee Kim, Paul Compton\n  \n### 2013\n\n* *[\"ClausIE: clause-based open information extraction\"](http:\u002F\u002Fresources.mpi-inf.mpg.de\u002Fd5\u002Fclausie\u002Fclausie-www13.pdf)* - WWW 2013 ([slides](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro13clausie-slides.pdf), [code](http:\u002F\u002Fresources.mpi-inf.mpg.de\u002Fd5\u002Fclausie\u002Fclausie-0-0-1.zip), [all resources](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fsoftware\u002Fclausie\u002F))\n\n  Luciano Del Corro, Rainer Gemulla\n  \n* *[\"Integrating Syntactic and Semantic Analysis into the Open Information Extraction Paradigm\"](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~moro\u002FMoroNavigli_IJCAI13.pdf)* - IJCAI 2013 ([resources](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F))\n\n  Andrea Moro, Roberto Navigli\n\n* *[\"Effectiveness and Efficiency of Open Relation Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD13-1043)* - EMNLP 2013 ([code](https:\u002F\u002Fgithub.com\u002FU-Alberta\u002Fexemplar))\n\n  Filipe de Sá Mesquita, Jordan Schmidek, Denilson Barbosa\n  \n* *[\"Open Information Extraction with Tree Kernels\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN13-1107)* - HLT-NAACL 2013\n \n  Ying Xu, Mi-Young Kim, Kevin Quinn, Randy Goebel, Denilson Barbosa\n  \n* *[\"Relation Extraction with Matrix Factorization and Universal Schemas\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN13-1008)* -  HLT-NAACL 2013 \n\n  Sebastian Riedel, Limin Yao, Andrew McCallum, Benjamin M. Marlin\n  \n* *[\"Open Information Extraction via Contextual Sentence Decomposition\"](http:\u002F\u002Fad-publications.cs.uni-freiburg.de\u002FICSC_csdie_BH_2013.pdf)* - ICSC 2013\n  \n  Hannah Bast, Elmar Haussmann\n  \n* *[\"Integrating Open and Closed Information Extraction: Challenges and First Steps\"](http:\u002F\u002Fceur-ws.org\u002FVol-1064\u002FDutta_Integrating.pdf)* - NLP-DBPEDIA@ISWC 2013\n\n  Arnab Dutta, Christian Meilicke, Mathias Niepert, Simone Paolo Ponzetto\n  \n* *[\"Open Information Extraction to KBP Relations in 3 Hours\"](https:\u002F\u002Fpdfs.semanticscholar.org\u002Fd431\u002F81fa9af5440360d4055e1ce7ddaaa6e82d77.pdf)* - TAC 2013\n\n  Stephen Soderland, John Gilmer, Robert Bart, Oren Etzioni, Daniel S. Weld\n  \n### 2014\n\n* *[\"ReNoun: Fact Extraction for Nominal Attributes\"](http:\u002F\u002Femnlp2014.org\u002Fpapers\u002Fpdf\u002FEMNLP2014038.pdf)* - EMNLP 2014\n  \t\n  Mohamed Yahya, Steven Whang, Rahul Gupta, Alon Y. Halevy\n    \n* *[\"ZORE: A Syntax-based System for Chinese Open Relation Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD14-1201)* - EMNLP 2014\n\n  Likun Qiu, Yue Zhang\n  \n* *[\"Canonicalizing Open Knowledge Bases\"](https:\u002F\u002Fsuchanek.name\u002Fwork\u002Fpublications\u002Fcikm2014.pdf)* - CIKM 2014\n\n  Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek\n  \n* *[\"Focused Entailment Graphs for Open IE Propositions\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW14-1610)* - CoNLL 2014\n\n  Omer Levy, Ido Dagan, Jacob Goldberger\n\n* *[\"Boosting Open Information Extraction with Noun-Based Relations\"](https:\u002F\u002Fpdfs.semanticscholar.org\u002F570c\u002Fce7b24c51f75da091b515baddce567128680.pdf)* - LREC 2014\n\n  Clarissa Castellã Xavier, Vera Lúcia Strube de Lima\n\n* *[\"Improving Open Relation Extraction via Sentence Re-Structuring\"](http:\u002F\u002Fwww.lrec-conf.org\u002Fproceedings\u002Flrec2014\u002Fpdf\u002F1038_Paper.pdf)* - LREC 2014\n\n  Jordan Schmidek, Denilson Barbosa\n\n* *[\"More Informative Open Information Extraction via Simple Inference\"](http:\u002F\u002Fad-publications.informatik.uni-freiburg.de\u002FECIR_csdie-inf_BH_2014.pdf)* - ECIR 2014\n\n  Hannah Bast, Elmar Haussmann\n  \n* *[\"Semantifying Triples from Open Information Extraction Systems\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F36881\u002F1\u002FFAIA264-0111.pdf)* - STAIRS 2014\n\n  Arnab Dutta, Christian Meilicke, Heiner Stuckenschmidt\n\n* *[\"Entity-Centric Coreference Resolution of Person Entities for Open Information Extraction\"](http:\u002F\u002Fwww.taln.upf.edu\u002Fpages\u002Fsepln2014\u002Ffull_papers\u002Fedited_paper_30.pdf)* - Procesamiento del Lenguaje Natural (2014)\n\n  Marcos García, Pablo Gamallo\n  \n* *[\"Open Information Extraction for Spanish Language based on Syntactic Constraints\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP14-3011.pdf)* - ACL (Student Research Workshop) (2014)\n\n  Alisa Zhila, Alexander Gelbukh\n  \n### 2015\n\n* *[\"Leveraging Linguistic Structure For Open Domain Information Extraction\"](https:\u002F\u002Fnlp.stanford.edu\u002Fpubs\u002F2015angeli-openie.pdf)* - ACL 2015 ([code (Java)](https:\u002F\u002Fstanfordnlp.github.io\u002FCoreNLP\u002Fopenie.html), [code (Python)](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python))\n\n  Gabor Angeli, Melvin Jose Johnson Premkumar, Christopher D. Manning\n\n* *[\"Open IE as an Intermediate Structure for Semantic Tasks\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP15-2050)* - ACL 2015\n\n  Gabriel Stanovsky, Ido Dagan, Mausam\n  \n* *[\"Large-Scale Information Extraction from Textual Definitions through Deep Syntactic and Semantic Analysis\"](https:\u002F\u002Ftransacl.org\u002Fojs\u002Findex.php\u002Ftacl\u002Farticle\u002Fview\u002F660)* - TACL 2015 ([resources](http:\u002F\u002Flcl.uniroma1.it\u002Fdefie\u002F))\n\n  Claudio Delli Bovi, Luca Telesca, Roberto Navigli\n  \n* *[\"Inferring Binary Relation Schemas for Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD15-1065)* - EMNLP 2015\n\n  Kangqi Luo, Xusheng Luo, Kenny Qili Zhu\n  \n* *[\"Knowledge Base Unification via Sense Embeddings and Disambiguation\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD15-1084)* - EMNLP 2015 ([resources](http:\u002F\u002Flcl.uniroma1.it\u002Fkb-unify\u002F))\n\n  Claudio Delli Bovi, Luis Espinosa Anke, Roberto Navigli\n  \n* *[\"CORE: Context-Aware Open Relation Extraction with Factorization Machines\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD15-1204)* - EMNLP 2015 ([code](https:\u002F\u002Fgithub.com\u002Ffabiopetroni\u002FCORE))\n\n  Fabio Petroni, Luciano Del Corro, Rainer Gemulla\n  \n* [*\"Multilingual Open Relation Extraction Using Cross-lingual Projection\"*](https:\u002F\u002Fstatic.googleusercontent.com\u002Fmedia\u002Fresearch.google.com\u002Fen\u002F\u002Fpubs\u002Farchive\u002F43449.pdf) - HLT-NAACL 2015\n\n  Manaal Faruqui, Shankar Kumar\n  \n* [*\"Enriching Structured Knowledge with Open Information\"*](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F38861\u002F1\u002Fp267.pdf) - WWW 2015\n\n  Arnab Dutta, Christian Meilicke, Heiner Stuckenschmidt\n  \n* *[\"SRDF: Korean Open Information Extraction using Singleton Property\"](http:\u002F\u002Fceur-ws.org\u002FVol-1486\u002Fpaper_55.pdf)* - ISWC 2015\n\n  Sangha Nam, YoungGyun Hahm, Sejin Nam, Key-Sun Choi\n\n* *[\"Multilingual Open Information Extraction\"](https:\u002F\u002Fgramatica.usc.es\u002F~gamallo\u002Fartigos-web\u002FEPIA2015.pdf)* - EPIA 2015\n\n  Pablo Gamallo, Marcos García\n  \n* *[\"Open information extraction based on lexical semantics\"](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1186\u002Fs13173-015-0023-2)* - J. Braz. Comp. Soc. 21 2015\n\n  Clarissa Castellã Xavier, Vera Lúcia Strube de Lima, Marlo Souza\n  \n### 2016\n\n* *[\"Nested Propositions in Open Information Extraction\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1006)* - EMNLP 2016 ([talk](https:\u002F\u002Fvimeo.com\u002F239245885))\n\n  Nikita Bhutani, H. V. Jagadish, Dragomir R. Radev\n\n* *[\"Creating a Large Benchmark for Open Information Extraction\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1252)* - EMNLP 2016 ([code](https:\u002F\u002Fgithub.com\u002FgabrielStanovsky\u002Foie-benchmark), [talk](https:\u002F\u002Fvimeo.com\u002F239251034))\n\n  Gabriel Stanovsky, Ido Dagan\n  \n* *[\"Porting an Open Information Extraction System from English to German\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1086)* - EMNLP 2016 ([code](https:\u002F\u002Fgithub.com\u002FUKPLab\u002Fprops-de))\n\n  Tobias Falke, Gabriel Stanovsky, Iryna Gurevych, Ido Dagan\n  \n* *[\"Relation Schema Induction using Tensor Factorization with Side Information\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD16-1040)* - EMNLP 2016 \n\n  Madhav Nimishakavi, Uday Singh Saini, Partha P. Talukdar\n  \n* *[\"Open Information Extraction Systems and Downstream Applications\"](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F604.pdf)* - IJCAI 2016\n\n  Mausam\n  \n* *[\"Demonyms and Compound Relational Nouns in Nominal Open IE\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fakbc16.pdf)* - AKBC@NAACL-HLT 2016\n\n  Harinder Pal, Mausam\n  \n* *[\"A Rule Based Open Information Extraction Method Using Cascaded Finite-State Transducer\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-31750-2_26)* - PAKDD 2016\n\n  Hailun Lin, Yuanzhuo Wang, Peng Zhang, Weiping Wang, Yinliang Yue, Zheng Lin\n\n* *[\"Getting More Out Of Syntax with PropS\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.01648.pdf)* - CoRR (2016)\n\n  Gabriel Stanovsky, Jessica Ficler, Ido Dagan, Yoav Goldberg\n\n* *[\"Improving Open Information Extraction for Semantic Web Tasks\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-662-49521-6_6)* -  Trans. Computational Collective Intelligence 21, 2016\n\n  Cheikh Kacfah Emani, Catarina Ferreira Da Silva, Bruno Fiés, Parisa Ghodous\n  \n* *[\"An Informativeness Approach to Open IE Evaluation\"](http:\u002F\u002Frali.iro.umontreal.ca\u002Frali\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublis\u002FAn_informativeness_approach_to_Open_IE_evaluation%5B1%5D.pdf)* - CICLing 2016 ([slides](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf), [code + data](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fdata\u002FCICLing_092.zip))\n\n  William Léchelle, Philippe Langlais\n  \n### 2017\n\n* *[\"MinIE: Minimizing Facts in Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD17-1278)* - EMNLP 2017 ([code](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002Fminie), [poster](https:\u002F\u002Fdws.informatik.uni-mannheim.de\u002Ffileadmin\u002Flehrstuehle\u002Fpi1\u002Fpeople\u002Frgemulla\u002Fpublications\u002Fgashteovski17minie-poster.pdf), [all resources](https:\u002F\u002Fdws.informatik.uni-mannheim.de\u002Fen\u002Fresources\u002Fsoftware\u002Fminie\u002F))\n\n  Kiril Gashteovski, Rainer Gemulla, Luciano Del Corro\n  \n* *[\"Answering Complex Questions Using Open Information Extraction\"](http:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002FTupleInf_ACL17.pdf)* - ACL 2017\n\n  Tushar Khot, Ashish Sabharwal, Peter Clark\n  \n* *[\"Pocket Knowledge Base Population\"](https:\u002F\u002Fwww.cs.jhu.edu\u002F~mdredze\u002Fpublications\u002F2017_acl_pocket_kb.pdf)* - ACL 2017\n  \n  Travis Wolfe, Mark Dredze, Benjamin Van Durme\n  \n* *[\"Bootstrapping for Numerical Open IE\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Facl17.pdf)* - ACL 2017\n\n  Swarnadeep Saha, Harinder Pal, Mausam\n\n* *[\"MT\u002FIE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FE17-2011)* - EACL 2017 ([code](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie))\n  \t\n  Kevin Duh, Benjamin Van Durme, Sheng Zhang\n  \n* *[Open Relation Extraction for Support Passage Retrieval: Merit and Open Issues\"](https:\u002F\u002Fwww.cs.unh.edu\u002F~dietz\u002Fappendix\u002Fopenie4ir\u002Fkadry-dietz-sigir2017-open-relation-extraction-for-support-passage-retrieval.pdf)* - SIGIR 2017\n\n  Amina Kadry, Laura Dietz\n    \n* *[\"Syntactic Representation Learning for Open Information Extraction on Web\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3041021.3054266)* - WWW 2017\n\n  Chengsen Ru, Jintao Tang, Shasha Li, Ting Wang\n    \n* *[\"MetaPAD: Meta Pattern Discovery from Massive Text Corpora\"](http:\u002F\u002Fwww.meng-jiang.com\u002Fpubs\u002Fmetapad-kdd17\u002Fmetapad-kdd17-paper.pdf)* ([code](https:\u002F\u002Fgithub.com\u002Fmjiang89\u002FMetaPAD))- KDD 2017\n\n  Meng Jiang, Jingbo Shang, Taylor Cassidy, Xiang Ren, Lance M. Kaplan, Timothy P. Hanratty, Jiawei Han\n  \n* *[\"RelVis: Benchmarking OpenIE Systems\"](http:\u002F\u002Fceur-ws.org\u002FVol-1963\u002Fpaper527.pdf)* - ISWC 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n  \n* *[\"A Consolidated Open Knowledge Representation for Multiple Texts\"](https:\u002F\u002Faclanthology.org\u002FW17-0902.pdf)* -  LSDSem@EACL 2017\n\n  Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martínez-Cámara, Iryna Gurevych, Ido Dagan\n\n* *[\"Open Relation Extraction and Grounding\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FI17-1086)* - IJCNLP 2017\n\n  Dian Yu, Lifu Huang, Heng Ji\n  \n* *[\"Selective Decoding for Cross-lingual Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FI17-1084)* - IJCNLP(1) 2017\n\n  Sheng Zhang, Kevin Duh, Benjamin Van Durme\n\n* *[\"An assessment of open relation extraction systems for the semantic web\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306437916304999)* - Inf. Syst. 71, 2017\n\n  Amal Zouaq, Michel Gagnon, Ludovic Jean-Louis\n  \n* *[\"An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-6944)* - IWCS 2017\n\n  Sheng Zhang, Rachel Rudinger, Benjamin Van Durme\n  \n* *[\"Discovering Relational Phrases for Qualia Roles Through Open Information Extraction\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-69548-8_6)* - KESW 2017\n\n  Giovanni Siragusa, Valentina Leone, Luigi Di Caro, Claudio Schifanella\n  \n* *[\"Open Relation Extraction Based on Core Dependency Phrase Clustering\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8005507)* - DSC 2017\n\n  Chengsen Ru, Shasha Li, Jintao Tang, Yi Gao, Ting Wang  \n  \n* *[\"Analysing Errors of Open Information Extraction Systems\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-5402)* - Workshop on Building Linguistically Generalizable NLP Systems @ EMNLP 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n  \n### 2018\n\n* *[\"Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002F2018_Logician_A_Unified_End-to-End_Neural_Approach_for_open_domain_IE(1).pdf)* - WSDM 2018\n\n  Mingming Sun, Xu Li, Xin Wang, Miao Fan, Yue Feng, Ping Li\n\n* *[\"Assertion-Based QA With Question-Aware Open Information Extraction\"](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002Fdownload\u002F16705\u002F16170)* - AAAI 2018\n  \t\n  Zhao Yan, Duyu Tang, Nan Duan, Shujie Liu, Wendi Wang, Daxin Jiang, Ming Zhou, Zhoujun Li\n  \n* *[\"Neural Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FP18-2065)* - ACL 2018\n\n  Lei Cui, Furu Wei, Ming Zhou\n  \n* *[\"Supervised Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN18-1081)* - NAACL-HLT 2018\n  \t\n  Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan\n  \n* [*\"Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD18-1236) - EMNLP 2018\n\n   Mingming Sun, Xu Li, Ping Li\n  \n* *[\"Open Information Extraction from Conjunctive Sentences\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1194)* - COLING 2018\n\n  Swarnadeep Saha, Mausam\n  \n* *[\"Graphene: Semantically-Linked Propositions in Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1195)* - COLING 2018 ([code](https:\u002F\u002Fgithub.com\u002FLambda-3\u002FGraphene), [documentation](http:\u002F\u002Flambda3.org\u002FGraphene\u002F))\n\n  Matthias Cetto, Christina Niklaus, André Freitas, Siegfried Handschuh\n  \n* *[\"Open Information Extraction on Scientific Text: An Evaluation\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1289)* - COLING 2018\n  \n  Paul T. Groth, Michael Lauruhn, Antony Scerri, Ron Daniel\n  \n* *[\"A Survey on Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1326)* - COLING 2018\n\n  Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh\n  \n* *[\"StuffIE: Semantic Tagging of Unlabeled Facets Using Fine-Grained Information Extraction\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271812)* - CIKM 2018\n\n  Radityo Eko Prasojo, Mouna Kacimi, Werner Nutt\n  \n* *[\"Towards Practical Open Knowledge Base Canonicalization\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271707)* - CIKM 2018\n\n   Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, Pengcheng Yin\n  \n* *[\"Open Information Extraction with Global Structure Constraints\"](http:\u002F\u002Fwww-bcf.usc.edu\u002F~xiangren\u002Fwww18_poster.pdf)* - WWW 2018\n\n  Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Frank F. Xu, Jiawei Han\n\n* *[\"CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3186030)* - WWW 2018 ([code](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi))\n  \n  Shikhar Vashishth, Prince Jain, Partha Talukdar\n\n* *[\"Revisiting the Task of Scoring Open IE Relations\"](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002Fsubmitted_to_LREC18.pdf)* ([poster](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2018-LREC-poster.pdf)) - LREC 2018\n\n  William Léchelle, Philippe Langlais\n  \n* *[\"Employing Semantic Context for Sparse Information Extraction Assessment\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3201407)* - TKDD 2018 ([resources](https:\u002F\u002Fgithub.com\u002Fpeipeilihfut\u002FAssessSparseIE))\n\n  Pei-Pei Li, Haixun Wang, Hongsong Li, Xindong Wu\n  \n* *[\"Open Information Extraction with Meta-pattern Discovery in Biomedical Literature\"](https:\u002F\u002Fyuzhimanhua.github.io\u002Fpapers\u002Fbcb18.pdf)* - BCB 2018\n\n  Xuan Wang, Yu Zhang, Qi Li, Yinyin Chen, Jiawei Han\n  \n* *[\"Modeling and Summarizing News Events Using Semantic Triples\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-93417-4_33)* - ESWC 2018\n\n  Radityo Eko Prasojo, Mouna Kacimi, Werner Nutt\n  \n* *[\"Disambiguating Open IE: Identifying Semantic Similarity in Relation Extraction by Word Embeddings\"](https:\u002F\u002Fwww.springerprofessional.de\u002Fen\u002Fdisambiguating-open-ie-identifying-semantic-similarity-in-relati\u002F16122888)* - PROPOR 2018\n\n  Leandro M. P. Sanches, Victor S. Cardel, Larissa S. Machado, Marlo Souza, Laís do Nascimento Salvador\n  \n* *[\"Task-Oriented Evaluation of Dependency Parsing with Open Information Extraction\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-99722-3_8)* - PROPOR 2018\n\n  Pablo Gamallo, Marcos Garcia\n  \n* *[\"Challenges of an Annotation Task for Open Information Extraction in Portuguese\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-99722-3_7)* - PROPOR 2018\n\n  Rafael Glauber, Leandro Souza de Oliveira, Cleiton Fernando Lima Sena, Daniela Barreiro Claro, Marlo Souza\n  \n* *[\"A systematic mapping study on open information extraction\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418303932)* -  Expert Syst. Appl. 2018\n\n  Rafael Glauber, Daniela Barreiro Claro\n  \n* *[\"Self-training on refined clause patterns for relation extraction\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0306457316303259?dgcid=raven_sd_recommender_email)* - Inf. Process. Manage. 54(4): 686-706 (2018)\n\n  Duc-Thuan Vo, Ebrahim Bagheri\n  \n* *[\"Supervised Neural Models Revitalize the Open Relation Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.09408.pdf)* - CoRR 2018\n\n  Shengbin Jia, Yang Xiang, Xiaojun Chen\n  \n* *[\"Chinese Open Relation Extraction and Knowledge Base Establishment\"](https:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002F10094_Paper.pdf)* - ACM Trans. Asian & Low-Resource Lang. Inf. Process. 2018 ([slides](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf), [code](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction))\n\n  Shengbin Jia, Shijia E, Maozhen Li, Yang Xiang\n  \n* *[Rule-based Indonesian Open Information Extraction\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8541293)* - ICAICTA 2018 \n\n  Ade Romadhony, Ayu Purwarianti, Dwi H. Widyantoro\n  \n* *[\"WiRe57 : A Fine-Grained Benchmark for Open Information Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.08962.pdf)* - CoRR 2018\n\n  William Léchelle, Fabrizio Gotti, Philippe Langlais\n  \n### 2019\n\n* *[\"OPIEC: An Open Information Extraction Corpus\"](https:\u002F\u002Fopenreview.net\u002Fpdf?id=HJxeGb5pTm)* - AKBC 2019 ([data + resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F), [code (data reading)](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002FOPIEC), [code (pipeline)](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002FOPIEC-pipeline))\n\n  Kiril Gashteovski, Sebastian Wanner, Sven Hertling, Samuel Broscheit, Rainer Gemulla\n  \n* *[\"MinScIE: Citation-centered Open Information Extraction\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F49216\u002F1\u002F_JCDL19Demo__MinScIE%20%284%29.pdf)* - JCDL 2019 ([code](https:\u002F\u002Fgithub.com\u002Fgkiril\u002FMinSCIE))\n\n  Anne Lauscher, Yide Song, Kiril Gashteovski\n  \n* *[\"EAL: A Toolkit and Dataset for Entity-Aspect Linking\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F49596\u002F1\u002FEAL.pdf)* - JCDL 2019 ([data](https:\u002F\u002Ffedericonanni.com\u002Feal-d\u002F), [code](https:\u002F\u002Fgithub.com\u002Fjinggz\u002FMaster-Thesis-EAL\u002Ftree\u002Fservice), [demo](http:\u002F\u002Ftools.dws.informatik.uni-mannheim.de\u002Feal))\n\n  Federico Nanni, Jingyi Zhang, Ferdinand Betz, Kiril Gashteovski\n\n* *[\"Integrating Local Context and Global Cohesiveness for Open Information Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.09931.pdf)* - WSDM 2019 ([code](https:\u002F\u002Fgithub.com\u002FGentleZhu\u002FReMine))\n\n  Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Ahmed El-Kishky, Jiawei Han\n\n* *[\"Open Information Extraction from Question-Answer Pairs\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.00172.pdf)* - NAACL 2019\n\n  Nikita Bhutani, Yoshihiko Suhara, Wang-Chiew Tan, Alon Halevy and H V Jagadish\n  \n* *[\"OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1083\u002F)* - NAACL 2019 ([data](https:\u002F\u002Fgithub.com\u002Fzhangdongxu\u002Frelation-inference-naacl19)) \n\n  Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Xin Luna Dong, Andrew McCallum\n  \n* *[\"OpenCeres: When Open Information Extraction Meets the Semi-Structured Web\"](http:\u002F\u002Flunadong.com\u002Fpublication\u002FopenCeres_naacl.pdf)* - NAACL 2019 ([video](https:\u002F\u002Fvimeo.com\u002F355837778), [slides](https:\u002F\u002Fhomes.cs.washington.edu\u002F~lockardc\u002FOpenCeres_NAACL_talk.pdf), [data](https:\u002F\u002Farchive.codeplex.com\u002F?p=swde))\n\n  Colin Lockard, Prashant Shiralkar and Xin Luna Dong \n  \n* *[\"Improving Open Information Extraction via Iterative Rank-Aware Learning\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1523)* - ACL 2019 ([code](https:\u002F\u002Fgithub.com\u002Fjzbjyb\u002Foie_rank))\n\n   Zhengbao Jiang, Pengcheng Yin and Graham Neubig\n   \n* *[\"Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1021.pdf)* - EMNLP 2019\n\n   Ruidong Wu, Yuan Yao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin and Maosong Sun\n   \n* *[\"Supervising Unsupervised Open Information Extraction Models\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1067.pdf)* - EMNLP 2019\n\n   Arpita Roy, Youngja Park, Taesung Lee and Shimei Pan\n   \n* *[\"CaRB: A Crowdsourced Benchmark for Open IE\"](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002F\u002Fpapers\u002Femnlp19.pdf)* - EMNLP 2019 ([code and data](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FCaRB))\n\n   Sangnie Bhardwaj, Samarth Aggarwal and Mausam\n   \n* *[\"CaRe: Open Knowledge Graph Embeddings\"](http:\u002F\u002Ftalukdar.net\u002Fpapers\u002FCaRe_EMNLP2019.pdf)* - EMNLP 2019 ([code](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FCaRE))\n\n   Swapnil Gupta, Sreyash Kenkre, Partha Talukdar\n   \n* *[\"Collaborative Policy Learning for Open Knowledge Graph Reasoning\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1269.pdf)* - EMNLP 2019 ([code](https:\u002F\u002Fgithub.com\u002FINK-USC\u002FCPL))\n \n   Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren\n   \n* *[\"Multi-Input Multi-Output Sequence Labeling for Joint Extraction of Fact and Condition Tuples from Scientific Text\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1029\u002F)* - EMNLP 2019\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh Chawla, Meng Jiang\n   \n* *[\"The Role of \"Condition\": A Novel Scientific Knowledge Graph Representation and Construction Model\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330942)* - KDD 2019\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n\n* *[\"Canonicalization of Open Knowledge Bases with Side Information from the Source Text\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8731346)* - ICDE 2019\n\n   Xueling Lin, Lei Chen\n   \n* *[\"Open Relation Extraction for Chinese Noun Phrases\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8903488)* - TKDE 2019\n\n   Chengyu Wang, Xiaofeng He, Aoying Zhou\n   \n* *[\"Divide and Extract – Disentangling Clause Splitting and Proposition Extraction\"](https:\u002F\u002Facl-bg.org\u002Fproceedings\u002F2019\u002FRANLP%202019\u002Fpdf\u002FRANLP047.pdf)* - RANLP 2019\n\n   Darina Gold, Torsten Zesch\n   \n* *[\"Exploiting Open IE for Deriving Multiple Premises Entailment Corpus\"](https:\u002F\u002Facl-bg.org\u002Fproceedings\u002F2019\u002FRANLP%202019\u002Fpdf\u002FRANLP144.pdf)* - RANLP 2019\n\n   Martin Víta, Jakub Klímek\n   \n* *[\"Lexicon-Grammar based Open Information Extraction from Natural Language Sentences in Italian\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417419306724)* - Expert Systems and Applications 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito, Giuseppe De Pietro\n   \n* *[\"Weakly Supervised, Data-Driven Acquisition of Rules for Open Information Extraction\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-18305-9_2)* - CAIAC 2019\n\n   Fabrizio GottiEmail, Philippe Langlais\n\n* *[\"Aligning Open IE Relations and KB Relations using a Siamese Network Based on Word Embedding\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002Fpapers\u002FW\u002FW19\u002FW19-0412\u002F)* - ICCS 2019\n\n   Rifki Afina Putri, Giwon Hong, Sung-Hyon Myaeng\n   \n* [*\"Contextualized Word Embeddings in a Neural Open Information Extraction Model\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-23281-8_31) - NLDB 2019\n\n   Injy Sarhan, Marco R. Spruit\n   \n* [*\"Multilingual Open Information Extraction: Challenges and Opportunities\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) -  Information 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n   \n* [*\"CTGA: Graph-based Biomedical Literature Search\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8983173) - IEEE International Conference on Bioinformatics and Biomedicine (BIBM)\n\n   Tianwen Jiang, Zhihan Zhang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n* [*\"When Lexicon-Grammar Meets Open Information Extraction: a Computational Experiment for Italian Sentences\"*](http:\u002F\u002Fceur-ws.org\u002FVol-2481\u002Fpaper36.pdf) -  CLiC-it 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*\"Towards a gold standard dataset for Open Information Extraction in Italian\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*\"Co-Clustering Triples from Open Information Extraction\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~kpal\u002Fpaper\u002FCOMAD_2020_kpal.pdf) - COMAD 2019\n\n   Koninika Pal, Vinh Thinh Ho, Gerhard Weikum\n   \n* [*Coherence and Salience-Based Multi-Document Relationship Mining*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F332735453_Coherence_and_Salience-Based_Multi-Document_Relationship_Mining) - APWeb-WAIM 2019\n\n   Yongpan Sheng, Zenglin Xu\n\n* *[\"Learning Open Information Extraction of Implicit Relations from Reading Comprehension Datasets\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07471)* - CoRR 2019\n\n   Jacob Beckerman, Theodore Christakis\n   \n### 2020\n\n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n\n* [*A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.167\u002F) - EMNLP 2020 ([resources](https:\u002F\u002Fsunbelbd.github.io\u002FOpen-Information-eXpression\u002F))\n\n   Mingming Sun, Wenyue Hua, Zoey Liu, Xin Wang, Kangjie Zheng, Ping Li\n\n\n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction*](http:\u002F\u002Fwww.cs.ox.ac.uk\u002Fpublications\u002Fpublication14256-abstract.html) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n\n\n* [*SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.02438.pdf) - EMNLP 2020\n\n   Xuming Hu, Chenwei Zhang, Yusong Xu, Lijie Wen, Philip S. Yu\n\n* [*\"OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03147) ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)) - EMNLP 2020\n\n  Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti\n\n* [*\"Multi2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.08128.pdf) ([code](https:\u002F\u002Fgithub.com\u002Fyoungbin-ro\u002FMulti2OIE)) - EMNLP 2020\n\n  Youngbin Ro, Yukyung Lee, Pilsung Kang\n  \n* [*\"On Aligning OpenIE Extractions with Knowledge Bases: A Case Study\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.eval4nlp-1.14\u002F) ([video](https:\u002F\u002Fslideslive.com\u002F38939720\u002Fon-aligning-openie-extractions-with-knowledge-bases-a-case-study), [slides](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002Fpi1\u002Fopiec\u002Fdsa-ota-talk-final.pdf), [resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F)) - Eval4NLP@EMNLP 2020\n\n   Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke\n\n* [*\"IMoJIE: Iterative Memory-Based Joint Open Information Extraction\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.521\u002F) ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie), [video](https:\u002F\u002Fslideslive.com\u002F38929035\u002Fimojie-iterative-memorybased-joint-open-information-extraction)) - ACL 2020\n\n   Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti\n   \n* [*\"Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.209\u002F) ([resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Folpbench\u002F), [video](https:\u002F\u002Fslideslive.com\u002F38929433\u002Fcan-we-predict-new-facts-with-open-knowledge-graph-embeddings-a-benchmark-for-open-link-prediction)) - ACL 2020\n\n   Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla\n\n* [*\"Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.717\u002F) ([video](https:\u002F\u002Fslideslive.com\u002F38928762\u002Flearning-interpretable-relationships-between-entities-relations-and-concepts-via-bayesian-structure-learning-on-open-domain-facts)) - ACL 2020\n\n   Jingyuan Zhang, Mingming Sun, Yue Feng, Ping Li\n\n* [*\"In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.137.pdf) ([code](https:\u002F\u002Fgithub.com\u002Frubenkruiper\u002FFOBIE), [video](https:\u002F\u002Fslideslive.com\u002F38928870\u002Fin-laymans-terms-semiopen-relation-extraction-from-scientific-texts)) - ACL 2020\n\n   Ruben Kruiper, Julian Vincent, Jessica Chen-Burger, Marc Desmulliez, Ioannis Konstas\n\n* *[\"Span Model for Open Information Extraction on Accurate Corpus\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.10879.pdf)* ([code](https:\u002F\u002Fgithub.com\u002Fzhanjunlang\u002FSpan_OIE))- AAAI 2020\n   \n   Junlang Zhan, Hai Zhao\n   \n* *[\"LOREM: Language-consistent Open Relation Extraction from Unstructured Text\"](https:\u002F\u002Frepository.tudelft.nl\u002Fislandora\u002Fobject\u002Fuuid%3A3d9cfa08-4a7f-41cc-afdd-a8902094228c)* ([code](https:\u002F\u002Fgithub.com\u002Ftomharting\u002FLOREM)) - WWW 2020\n\n   Tom Harting, Sepideh Mesbah, Christoph Lofi\n   \n* *[\"Extracting Knowledge from Web Text with Monte Carlo Tree Search\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380010)* - WWW 2020\n\n   Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li\n   \n* *[\"MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-62005-9_23)* - WISE 2020\n\n   Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen\n\n   \n* [*An Advantage Actor-Critic Algorithm with Confidence Exploration for Open Information Extraction\"*](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611976236.25) - SDM 2020\n\n   Guiliang Liu, Xu Li, Miningming Sun, Ping Li\n\n   \n* *[\"Chinese Open Relation Extraction with Pointer-Generator Networks\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9172882\u002Freferences#references)* - DSC 2020\n\n   Ziheng Cheng, Xu Wu, Xiaqing Xie, Jingchen Wu\n   \n* *[Explainable OpenIE Classifier with Morpho-syntactic Rules\"](http:\u002F\u002Fceur-ws.org\u002FVol-2693\u002Fpaper1.pdf)* - HI4NLP@ECAI 2020 \n\n   Bruno Cabral, Marlo Souza, Daniela Barreiro Claro\n   \n* [*Language Models are Open Knowledge Graphs*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11967) - CoRR 2020\n\n   Chenguang Wang, Xiao Liu, Dawn Song\n   \n* [*\"Hybrid Neural Tagging Model for Open Relation Extraction\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.01761.pdf) - CoRR 2020 ([data](https:\u002F\u002Fgithub.com\u002FTJUNLP\u002FNSL4OIE))\n\n   Shengbin Jia, Yang Xiang\n   \n* [*\"Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09610.pdf) - CoRR 2020\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n* [*\"Tag and Correct: Question Aware Open Information Extraction with Two-Stage Decoding\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.07406.pdf) - CoRR 2020\n\n   Martin Kuo, Yaobo Liang, Lei Ji, Nan Duan, Linjun Shou, Ming Gong, Peng Chen\n   \n* [*\"Abstractive Query Focused Summarization with Query-Free Resources\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.14774) - CoRR 2020\n\n   Yumo Xu, Mirella Lapata\n\n### 2021\n\n* [*\"CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.00793.pdf) - ACL 2021\n\n   Zhengbao Jiang, Jialong Han, Bunyamin Sisman, Xin Luna Dong\n   \n* [*\"DocOIE: A Document-level Context-Aware Dataset for OpenIE\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.210\u002F) - ACL 2021\n\n   Kuicai Dong, Zhao Yilin, Aixin Sun, Jung-Jae Kim, Xiaoli Li\n   \n* [*\"OKGIT: Open Knowledge Graph Link Prediction with Implicit Types\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.225\u002F) - ACL 2021\n\n   \tChandrahas, Partha Pratim Talukdar\n    \n* [*\"Maximal Clique Based Non-Autoregressive Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.764\u002F) - EMNLP 2021\n\n    Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang\n    \n* [*\"Zero-Shot Information Extraction as a Unified Text to Triple Translation\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.94\u002F) - EMNLP 2021 ([code](https:\u002F\u002Fgithub.com\u002Fcgraywang\u002Fdeepex))\n\n    Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song\n    \n* [*\"Open Knowledge Graphs Canonicalization using Variational Autoencoders\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.811\u002F) - EMNLP 2021 ([code](https:\u002F\u002Fgithub.com\u002FIBM\u002FOpen-KG-canonicalization))\n\n    Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo\n   \n* [*\"LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2021.eacl-main.222\u002F) - EACL 2021 ([code and data](https:\u002F\u002Fgithub.com\u002FJacobsolawetz\u002Flarge-scale-oie)) \n\n   Jacob Solawetz, Stefan Larson\n\n* [*\"Open Hierarchical Relation Extraction\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.452.pdf) - NAACL 2021 ([code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FOHRE))\n\n   Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun\n\n* [*\"Semi-Open Information Extraction\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3442381.3450029) - WWW 2021\n\n   Bowen Yu, Zhenyu Zhang, Jiawei Sheng, Tingwen Liu, Yubin Wang, Yucheng Wang, Bin Wang\n   \n* [*\"Joint Open Knowledge Base Canonicalization and Linking\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3452776) - SIGMOD 2021\n\n   \tYinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan\n    \n* [*\"TENET: Joint Entity and Relation Linking with Coherence Relaxation\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n\n* [*\"Multi-Grained Dependency Graph Neural Network for Chinese Open Information Extraction\"*](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n   \n* [*\"CaSIE: Canonicalize and Informative Selection of the OpenIE system\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9458825) - ICDE 2021\n\n   Hao Xin, Xueling Lin, Lei Chen\n   \n* *[PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation\"](https:\u002F\u002Faclanthology.org\u002F2021.eacl-srw.4\u002F)* - Student Research Workshop @ EACL\n\n   Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis\n   \n### 2022\n\n* [*\"BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.307\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fgkiril\u002Fbenchie))\n\n   Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n* [*\"MILIE: Modular & Iterative Multilingual Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.478\u002F) - ACL 2022 \n\n   Bhushan Kotnis, Kiril Gashteovski, Daniel Rubio, Ammar Shaker, Vanesa Rodriguez-Tembras, Makoto Takamoto, Mathias Niepert, Carolin Lawrence\n\n* [*Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.179\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fmoie))\n\n   Keshav Kolluru, Muqeeth Mohammed, Shubham Mittal, Soumen Chakrabarti, Mausam\n\n* [*\"OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.430\u002F) - ACL 2022 \n\n   Xin Wang, Minlong Peng, Mingming Sun, Ping Li\n   \n* [*\"Open Relation Modeling: Learning to Define Relations between Entities\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.26\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fjeffhj\u002Fopen-relation-modeling))\n\n   Jie Huang, Kevin Chang, Jinjun Xiong, Wen-mei Hwu\n   \n* [*\"DeepStruct: Pretraining of Language Models for Structure Prediction\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.67\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fcgraywang\u002Fdeepstruct))\n\n   Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song\n      \n* [*\"AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-demo.5\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fnfriedri\u002Fannie-annotation-platform))\n\n   Niklas Friedrich, Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n* [*\"CompactIE: Compact Facts in Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2022.naacl-main.65\u002F) - NAACL 2022 ([code](https:\u002F\u002Fgithub.com\u002FFarimaFatahi\u002FCompactIE))\n\n   Farima Fatahi Bayat, Nikita Bhutani, H. V. Jagadish\n\n* [*\"DetIE: Multilingual Open Information Extraction Inspired by Object Detection\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8073.VasilkovskyM.pdf) - AAAI 2022 ([code](https:\u002F\u002Fgithub.com\u002Fsberbank-ai\u002FDetIE))\n\n   Michael Vasilkovsky, Anton Alekseev, Valentin Malykh, Ilya Shenbin, Elena Tutubalina, Dmitriy Salikhov, Mikhail Stepnov, Andrey Chertok, Sergey I. Nikolenko\n\n* [*\"A Survey on Neural Open Information Extraction: Current Status and Future Directions\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.11725.pdf) - IJCAI 2022\n\n   Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Jian Sun\n   \n* [*\"Open Information Extraction from 2007 to 2022 – A Survey\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2208.08690.pdf) - CoRR 2022\n\n   Pai Liu, Wenyang Gao, Wenjie Dong, Songfang Huang, Yue Zhang\n\n\n## Papers grouped by category\n\n### Surveys\n\n* *[\"Open Information Extraction Systems and Downstream Applications\"](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F604.pdf)* - IJCAI 2016\n\n  Mausam\n  \n* *[\"A Survey on Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1326)* - COLING 2018\n\n  Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh\n\n* *[\"A systematic mapping study on open information extraction\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418303932)* -  Expert Syst. Appl. 2018\n\n  Rafael Glauber, Daniela Barreiro Claro\n  \n* [*\"Multilingual Open Information Extraction: Challenges and Opportunities\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) -  Information 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n   \n* [*\"A Survey on Neural Open Information Extraction: Current Status and Future Directions\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.11725.pdf) - IJCAI 2022\n\n   Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Jian Sun\n\n* [*\"Open Information Extraction from 2007 to 2022 – A Survey\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2208.08690.pdf) - CoRR 2022\n\n   Pai Liu, Wenyang Gao, Wenjie Dong, Songfang Huang, Yue Zhang\n\n### Evaluation\n\n* *[\"Creating a Large Benchmark for Open Information Extraction\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1252)* - EMNLP 2016 ([code](https:\u002F\u002Fgithub.com\u002FgabrielStanovsky\u002Foie-benchmark), [talk](https:\u002F\u002Fvimeo.com\u002F239251034))\n\n  Gabriel Stanovsky, Ido Dagan\n\n* *[\"An Informativeness Approach to Open IE Evaluation\"](http:\u002F\u002Frali.iro.umontreal.ca\u002Frali\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublis\u002FAn_informativeness_approach_to_Open_IE_evaluation%5B1%5D.pdf)* - CICLing 2016 ([slides](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf), [code + data](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fdata\u002FCICLing_092.zip))\n\n  William Léchelle, Philippe Langlais\n\n* *[\"An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-6944)* - IWCS 2017\n\n  Sheng Zhang, Rachel Rudinger, Benjamin Van Durme\n\n* *[\"An assessment of open relation extraction systems for the semantic web\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306437916304999)* - Inf. Syst. 71, 2017\n\n  Amal Zouaq, Michel Gagnon, Ludovic Jean-Louis\n  \n* *[\"RelVis: Benchmarking OpenIE Systems\"](http:\u002F\u002Fceur-ws.org\u002FVol-1963\u002Fpaper527.pdf)* - ISWC 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n  \n* *[\"Analysing Errors of Open Information Extraction Systems\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-5402)* - Workshop on Building Linguistically Generalizable NLP Systems @ EMNLP 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n\n* *[\"Open Information Extraction on Scientific Text: An Evaluation\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1289)* - COLING 2018\n  \n  Paul T. Groth, Michael Lauruhn, Antony Scerri, Ron Daniel\n  \n* *[\"WiRe57 : A Fine-Grained Benchmark for Open Information Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.08962.pdf)* - CoRR 2018\n\n  William Léchelle, Fabrizio Gotti, Philippe Langlais\n  \n* *[\"CaRB: A Crowdsourced Benchmark for Open IE\"](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002F\u002Fpapers\u002Femnlp19.pdf)* - EMNLP 2019 ([code and data](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FCaRB))\n\n   Sangnie Bhardwaj, Samarth Aggarwal and Mausam\n   \n* [*\"Towards a gold standard dataset for Open Information Extraction in Italian\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n   \n* [*\"On Aligning OpenIE Extractions with Knowledge Bases: A Case Study\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.eval4nlp-1.14\u002F) ([video](https:\u002F\u002Fslideslive.com\u002F38939720\u002Fon-aligning-openie-extractions-with-knowledge-bases-a-case-study), [slides](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002Fpi1\u002Fopiec\u002Fdsa-ota-talk-final.pdf), [resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F)) - Eval4NLP@EMNLP 2020\n\n   Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke\n   \n* [*\"BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.307\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fgkiril\u002Fbenchie))\n\n   Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n  \n### OIE for downstream applications\n\nOIE's output has been shown to be a useful input for many downstream tasks. In this section, several downstream tasks that benefited from OIE output are listed. \n\n#### Question Answering\n\n* [*\"Triple-Fact Retriever: An explainable reasoning retrieval model for multi-hop QA problem\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835400) - ICDE 2022\n\n   Chengmin Wu, Enrui Hu, Ke Zhan, Lan Luo, Xinyu Zhang, Hao Jiang, Qirui Wang, Zhao Cao, Fan Yu, Lei Chen\n\n* [*\"Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting\"*](https:\u002F\u002Faclanthology.org\u002F2021.acl-long.465\u002F) - ACL 2021\n\n   Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng\n   \n* [*\"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs\"*](https:\u002F\u002Faclanthology.org\u002FD19-1428.pdf) - EMNLP 2019\n\n   Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes\n\n* [*\"Assertion-based QA with Question-Aware Open Information Extraction\"*](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002Fdownload\u002F16705\u002F16170) AAAI 2018\n\n  Zhao Yan, Duyu Tang, Nan Duan, Shujie Liu, Wendi Wang, Daxin Jiang, Ming Zhou, Zhoujun Li\n\n* *[\"Answering Complex Questions Using Open Information Extraction\"](http:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002FTupleInf_ACL17.pdf)* - ACL 2017\n\n  Tushar Khot, Ashish Sabharwal, Peter Clark\n\n* [*\"Paraphrase-Driven Learning for Open Question Answering\"*](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP13-1158) ACL 2013 \n\n  Anthony Fader, Luke S. Zettlemoyer, Oren Etzioni\n  \n#### Slot Filling\n\n* [*\"Open Information Extraction to KBP Relations in 3 Hours\"*](https:\u002F\u002Fpdfs.semanticscholar.org\u002Fd431\u002F81fa9af5440360d4055e1ce7ddaaa6e82d77.pdf) - TAC 2013\n\n  Stephen Soderland, John Gilmer, Robert Bart, Oren Etzioni, Daniel S. Weld\n  \n* *[\"Leveraging Linguistic Structure For Open Domain Information Extraction\"](https:\u002F\u002Fnlp.stanford.edu\u002Fpubs\u002F2015angeli-openie.pdf)* - ACL 2015 ([code (Java)](https:\u002F\u002Fstanfordnlp.github.io\u002FCoreNLP\u002Fopenie.html), [code (Python)](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python))\n\n  Gabor Angeli, Melvin Jose Johnson Premkumar, Christopher D. Manning\n  \n* *[\"University of Washington System for 2015 KBP Cold Start Slot Filling\"](https:\u002F\u002Fwww.cs.rochester.edu\u002Fu\u002Fgkim21\u002Fpapers\u002FUWashington-KBP2015.pdf)* - TAC 2015\n\n   Stephen Soderland, Natalie Hawkins, Gene L. Kim, Daniel S. Weld\n   \n* *[\"Combining Open IE and Distant Supervision for KBP Slot Filling\"](https:\u002F\u002Ftac.nist.gov\u002Fpublications\u002F2015\u002Fparticipant.papers\u002FTAC2015.UWashington.proceedings.pdf)* - TAC 2015\n\n   \tStephen Soderland, Natalie Hawkins, John Gilmer, Daniel S. Weld\n   \n* *[\"Open Relation Extraction and Grounding\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FI17-1086\u002F)* -  IJCNLP 2017\n\n   Dian Yu, Lifu Huang, Heng Ji\n\n\n#### Event Extraction\n\n* [*\"Generating Coherent Event Schemas at Scale\"*](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Femnlp-2013-niranjan.pdf) - EMNLP 2013\n\n  Niranjan Balasubramanian, Stephen Soderland, Mausam, Oren Etzioni\n\n* [*\"Cross-document Event Identity via Dense Annotation\"*](https:\u002F\u002Faclanthology.org\u002F2021.conll-1.39\u002F) - CoNLL 2021\n\n   Adithya Pratapa, Zhengzhong Liu, Kimihiro Hasegawa, Linwei Li, Yukari Yamakawa, Shikun Zhang, Teruko Mitamura\n\n#### Text Summarization\n\n* [*\"Facts That Matter\"*](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD18-1129) - EMNLP 2018\n\n  Marco Ponza, Luciano Del Corro, Gerhard Weikum\n  \n* [*\"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs\"*](https:\u002F\u002Faclanthology.org\u002FD19-1428.pdf) - EMNLP 2019\n\n   Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes\n  \n* [*\"Coherence and Salience-Based Multi-Document Relationship Mining\"*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F332735453_Coherence_and_Salience-Based_Multi-Document_Relationship_Mining) - APWeb-WAIM 2019\n\n   Yongpan Sheng, Zenglin Xu\n   \n* [*\"FAR-ASS: Fact-aware reinforced abstractive sentence summarization\"*](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0306457320309675) - Information Processing & Management 2021\n\n   Mengli Zhanga, Gang Zhoua, Wanting Yua, Wenfen Liu\n   \n* [*\"Summary Explorer: Visualizing the State of the Art in Text Summarization\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-demo.22\u002F) - EMNLP 2021\n\n   Shahbaz Syed, Tariq Yousef, Khalid Al Khatib, Stefan Jänicke, Martin Potthast\n\n   \n* [*\"Generating Query Focused Summaries from Query-Free Resources\"*](https:\u002F\u002Faclanthology.org\u002F2021.acl-long.475\u002F) - ACL 2021\n\n   Yumo Xu, Mirella Lapata\n   \n* [*\"Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters\"*](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.380.pdf) - NAACL 2021\n\n   Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, Markus Dreyer\n   \n* [*\"Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs\"*](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.109\u002F) - NAACL 2021\n\n   Jiaao Chen, Diyi Yang\n\n   \n* [*\"Focus on the Action: Learning to Highlight and Summarize Jointly for Email To-Do Items Summarization\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.323\u002F) - ACL 2022\n\n   Kexun Zhang, Jiaao Chen, Diyi Yang\n   \n* [*\"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations\"*](https:\u002F\u002Faclanthology.org\u002F2022.naacl-main.236\u002F) - NAACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Famazon-research\u002Ffact-graph))\n\n   Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal\n\n#### Knowledge Base Population\n\n* [*\"Pocket Knowledge Base Population\"*](https:\u002F\u002Fwww.cs.jhu.edu\u002F~mdredze\u002Fpublications\u002F2017_acl_pocket_kb.pdf) - ACL 2017\n\n  Travis Wolfe, Mark Dredze, Benjamin Van Durme\n  \n* [*KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking\"*](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp1035-lin.pdf) - PVLDB 2020\n\n  Xueling Lin, Haoyang Li, Hao Xin, Zijian Li, Lei Chen\n  \n#### Knowledge Base Construction\n\n* *[\"The Role of \"Condition\": A Novel Scientific Knowledge Graph Representation and Construction Model\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330942)* - KDD 2019\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n#### Entity Linking\n\n* [*\"TENET: Joint Entity and Relation Linking with Coherence Relaxation\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n    \n#### Relation Linking\n\n* [*\"TENET: Joint Entity and Relation Linking with Coherence Relaxation\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n    \n* [*\"Capturing Knowledge in Semantically-typed Relational Patterns to Enhance Relation Linking\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3148011.3148031) - K-CAP 2017\n\n    Kuldeep Singh, Isaiah Onando Mulang', Ioanna Lytra, Mohamad Yaser Jaradeh, Ahmad Sakor, Maria-Esther Vidal, Christoph Lange, Sören Auer\n   \n#### Open Link Prediction\n\n* [*\"OKGIT: Open Knowledge Graph Link Prediction with Implicit Types\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.225\u002F) - ACL 2021\n\n   \tChandrahas, Partha Pratim Talukdar\n    \n* [*\"Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.209\u002F) ([resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Folpbench\u002F), [video](https:\u002F\u002Fslideslive.com\u002F38929433\u002Fcan-we-predict-new-facts-with-open-knowledge-graph-embeddings-a-benchmark-for-open-link-prediction)) - ACL 2020\n\n   Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla\n   \n#### Relation Extraction\n\n* [*\"RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information\"*](https:\u002F\u002Faclanthology.org\u002FD18-1157.pdf) - EMNLP 2018\n\n   Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga, Chiranjib Bhattacharyya, Partha Talukdar\n\n#### Relating Entities\n\n* [*\"Relating Legal Entities via Open Information Extraction\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-14401-2_17) - MTSR 2018\n  \n  Giovanni Siragusa, Rohan Nanda, Valeria De Paiva, Luigi Di Caro\n  \n#### Story Comprehension\n\n* [*\"Enhanced Story Comprehension for Large Language Models through Dynamic Document-Based Knowledge Graphs\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-10221.AndrusB.pdf) - AAAI 2022\n\n   Berkeley Andrus, Yeganeh Nasiri, Jay Cui, Ben Cullen, Nancy Fulda\n\n#### Text Generation\n\n* [*\"An unsupervised joint system for text generation from knowledge graphs and semantic parsing\"*](https:\u002F\u002Faclanthology.org\u002F2020.emnlp-main.577.pdf) - EMNLP 2020\n\n   Martin Schmitt, Sahand Sharifzadeh, Volker Tresp, Hinrich Schütze\n\n#### Video Grounding\n\n* *[\"Interventional Video Grounding With Dual Contrastive Learning\"](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FNan_Interventional_Video_Grounding_With_Dual_Contrastive_Learning_CVPR_2021_paper.pdf)* - CVPR 2021\n\n  Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu\n  \n### OIE in Different Languages\n\nMost of the OIE systems are focused on extractions made from text written on English. However, some OIE systems either are focused on a language other than English, or are multilingual. In this section, OIE systems on languages other than English or multilingual OIE systems are listed. \n\n#### Multilingual OIE Systems\n\n* [*\"MILIE: Modular & Iterative Multilingual Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.478\u002F) - ACL 2022 \n\n   Bhushan Kotnis, Kiril Gashteovski, Daniel Rubio, Ammar Shaker, Vanesa Rodriguez-Tembras, Makoto Takamoto, Mathias Niepert, Carolin Lawrence\n   \n* [*Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.179\u002F) - ACL 2022 ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fmoie))\n\n   Keshav Kolluru, Muqeeth Mohammed, Shubham Mittal, Soumen Chakrabarti, Mausam\n\n* [*\"DetIE: Multilingual Open Information Extraction Inspired by Object Detection\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8073.VasilkovskyM.pdf) - AAAI 2022 ([code](https:\u002F\u002Fgithub.com\u002Fsberbank-ai\u002FDetIE)\n\n   Michael Vasilkovsky, Anton Alekseev, Valentin Malykh, Ilya Shenbin, Elena Tutubalina, Dmitriy Salikhov, Mikhail Stepnov, Andrey Chertok, Sergey I. Nikolenko\n\n\n* [*\"Multi2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.08128.pdf) ([code](https:\u002F\u002Fgithub.com\u002Fyoungbin-ro\u002FMulti2OIE)) - EMNLP 2020\n\n  Youngbin Ro, Yukyung Lee, Pilsung Kang\n\n* *[\"LOREM: Language-consistent Open Relation Extraction from Unstructured Text\"](https:\u002F\u002Frepository.tudelft.nl\u002Fislandora\u002Fobject\u002Fuuid%3A3d9cfa08-4a7f-41cc-afdd-a8902094228c)* ([code](https:\u002F\u002Fgithub.com\u002Ftomharting\u002FLOREM)) - WWW 2020\n\n   Tom Harting, Sepideh Mesbah, Christoph Lofi\n   \n* *[Explainable OpenIE Classifier with Morpho-syntactic Rules\"](http:\u002F\u002Fceur-ws.org\u002FVol-2693\u002Fpaper1.pdf)* - HI4NLP@ECAI 2020 \n\n   Bruno Cabral, Marlo Souza, Daniela Barreiro Claro\n\n* [*\"Multilingual Open Information Extraction: Challenges and Opportunities\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) -  Information 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n\n* [*\"Multilingual Open Relation Extraction Using Cross-lingual Projection\"*](https:\u002F\u002Fstatic.googleusercontent.com\u002Fmedia\u002Fresearch.google.com\u002Fen\u002F\u002Fpubs\u002Farchive\u002F43449.pdf) - HLT-NAACL 2015\n\n  Manaal Faruqui, Shankar Kumar\n  \n* *[\"MT\u002FIE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FE17-2011)* - EACL 2017 ([code](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie))\n  \t\n  Kevin Duh, Benjamin Van Durme, Sheng Zhang\n\n* [*\"Multilingual Open Information Extraction\"*](https:\u002F\u002Fgramatica.usc.es\u002F~gamallo\u002Fartigos-web\u002FEPIA2015.pdf) - EPIA 2015\n\n  Pablo Gamallo, Marcos García\n\n#### OIE Systems for German Language\n\n* [*\"GerIE - An Open Information Extraction System for the German Language\"*](http:\u002F\u002Fwww.jucs.org\u002Fjucs_24_1\u002Fgerie_an_open_information\u002Fjucs_24_01_0002_0024_bassa.pdf) - J. UCS 2018\n\n  Akim Bassa, Mark Kröll, Roman Kern\n  \n* [*\"Porting an Open Information Extraction System from English to German\"*](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1086) - EMNLP 2016 ([code](https:\u002F\u002Fgithub.com\u002FUKPLab\u002Fprops-de))\n\n  Tobias Falke, Gabriel Stanovsky, Iryna Gurevych, Ido Dagan\n\n#### OIE Systems for Portugese Language\n\n* [*\"Challenges of an Annotation Task for Open Information Extraction in Portuguese\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-99722-3_7) - PROPOR 2018\n\n  Rafael Glauber, Leandro Souza de Oliveira, Cleiton Fernando Lima Sena, Daniela Barreiro Claro, Marlo Souza\n\n* [*\"Inference Approach to Enhance a Portuguese Open Information Extraction\"*](http:\u002F\u002Fwww.scitepress.org\u002FPapers\u002F2017\u002F63382\u002F63382.pdf) - ICEIS 2017\n  \n  Cleiton Fernando Lima Sena, Rafael Glauber, Daniela Barreiro Claro\n  \n* [*\"DependentIE: An Open Information Extraction system on Portuguese by a Dependence Analysis\"*](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FRafael_Glauber\u002Fpublication\u002F324759625_DependentIE_An_Open_Information_Extraction_system_on_Portuguese_by_a_Dependence_Analysis\u002Flinks\u002F5ae0e48faca272fdaf8d8979\u002FDependentIE-An-Open-Information-Extraction-system-on-Portuguese-by-a-Dependence-Analysis.pdf) - ENIAC 2017\n\n  Leandro Souza de Oliveira, Rafael Glauber, Daniela Barreiro Claro\n  \n#### OIE Systems for Spanish Language\n\n* *[\"Open Information Extraction for Spanish Language based on Syntactic Constraints\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP14-3011.pdf)* - ACL (Student Research Workshop) (2014)\n\n  Alisa Zhila, Alexander Gelbukh\n  \n#### OIE Systems for Chinese Language\n\n* *[\"ZORE: A Syntax-based System for Chinese Open Relation Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD14-1201)* - EMNLP 2014\n\n  Likun Qiu, Yue Zhang\n  \n* *[\"Chinese Open Relation Extraction and Knowledge Base Establishment\"](https:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002F10094_Paper.pdf)* - ACM Trans. Asian & Low-Resource Lang. Inf. Process. 2018 ([slides](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf), [code](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction))\n\n  Shengbin Jia, Shijia E, Maozhen Li, Yang Xiang\n  \n* *[\"Open Relation Extraction for Chinese Noun Phrases\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8903488)* - TKDE 2019\n\n   Chengyu Wang, Xiaofeng He, Aoying Zhou\n   \n* *[\"Chinese Open Relation Extraction with Pointer-Generator Networks\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9172882\u002Freferences#references)* - DSC 2020\n\n   Ziheng Cheng, Xu Wu, Xiaqing Xie, Jingchen Wu\n   \n* [*\"Multi-Grained Dependency Graph Neural Network for Chinese Open Information Extraction\"*](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n  \n#### OIE Systems for Persian Language\n\n* [*\"RePersian:An Efficient Open Information Extraction Tool in Persian\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9122301\u002Fauthors#authors) - ICWR 2020\n\n  Raana Saheb-Nassagh, Majid Asgari, Behrouz Minaei-Bidgoli\n\n* [*\"A recursive algorithm for open information extraction from Persian texts\"*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F325977333_A_recursive_algorithm_for_open_information_extraction_from_Persian_texts) - IJCAT 2018\n\n  Mahmoud Rahat, Alireza Talebpour, Seyedamin Monemian\n  \n* [*\"Open information extraction as an intermediate semantic structure for Persian text summarization\"*](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs00799-018-0244-z) - Int. J. on Digital Libraries (2018)\n\n  Mahmoud Rahat, Alireza Talebpour\n  \n* [*\"Parsa: An open information extraction system for Persian\"*](https:\u002F\u002Facademic.oup.com\u002Fdsh\u002Farticle\u002F33\u002F4\u002F874\u002F4951677) - DSH 2018\n\n  Mahmoud Rahat, Alireza Talebpour\n  \n#### OIE Systems for Italian Language\n\n* *[\"Lexicon-Grammar based Open Information Extraction from Natural Language Sentences in Italian\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417419306724)* - Expert Systems and Applications 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito, Giuseppe De Pietro\n   \n* [*\"Towards a gold standard dataset for Open Information Extraction in Italian\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n#### OIE Systems for Indonesian Language\n\n* *[Rule-based Indonesian Open Information Extraction\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8541293)* - ICAICTA 2018 \n\n  Ade Romadhony, Ayu Purwarianti, Dwi H. Widyantoro\n  \n#### OIE Systems for Greek Language\n\n* *[PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation\"](https:\u002F\u002Faclanthology.org\u002F2021.eacl-srw.4\u002F)* - Student Research Workshop @ EACL\n\n   Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis\n\n### Supervised OIE\n\n* [*\"Supervised Open Information Extraction\"*](https:\u002F\u002Faclweb.org\u002Fanthology\u002FN18-1081) - NAACL-HLT 2018\n\n  Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan\n\n* [*\"Neural Open Information Extraction\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.04270.pdf) - ACL 2018\n\n  Lei Cui, Furu Wei, Ming Zhou\n  \n* *[\"Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002F2018_Logician_A_Unified_End-to-End_Neural_Approach_for_open_domain_IE(1).pdf)* - WSDM 2018\n\n  Mingming Sun, Xu Li, Xin Wang, Miao Fan, Yue Feng, Ping Li\n  \n* [*\"Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD18-1236) - EMNLP 2018\n\n   Mingming Sun, Xu Li, Ping Li\n   \n* *[\"Supervising Unsupervised Open Information Extraction Models\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1067.pdf)* - EMNLP 2019\n\n   Arpita Roy, Youngja Park, Taesung Lee and Shimei Pan\n   \n* [*\"Contextualized Word Embeddings in a Neural Open Information Extraction Model\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-23281-8_31) - NLDB 2019\n\n   Injy Sarhan, Marco R. Spruit\n\n* [*\"Weakly Supervised, Data-Driven Acquisition of Rules for Open Information Extraction\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-18305-9_2) - CAIAC 2019\n\n   Fabrizio GottiEmail, Philippe Langlais\n   \n* [*\"Learning Open Information Extraction of Implicit Relations from Reading Comprehension Datasets\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07471) - CoRR 2019\n\n   Jacob Beckerman, Theodore Christakis\n   \n* *[\"Span Model for Open Information Extraction on Accurate Corpus\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.10879.pdf)* ([code](https:\u002F\u002Fgithub.com\u002Fzhanjunlang\u002FSpan_OIE))- AAAI 2020\n   \n   Junlang Zhan, Hai Zhao\n   \n* *[\"Extracting Knowledge from Web Text with Monte Carlo Tree Search\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380010)* - WWW 2020\n\n   Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li\n   \n* [*An Advantage Actor-Critic Algorithm with Confidence Exploration for Open Information Extraction\"*](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611976236.25) - SDM 2020\n\n   Guiliang Liu, Xu Li, Miningming Sun, Ping Li\n   \n* [*\"Hybrid Neural Tagging Model for Open Relation Extraction\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.01761.pdf) - CoRR 2020 ([data](https:\u002F\u002Fgithub.com\u002FTJUNLP\u002FNSL4OIE))\n\n   Shengbin Jia, Yang Xiang   \n   \n* [*\"IMoJIE: Iterative Memory-Based Joint Open Information Extraction\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.521\u002F) ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie)) - ACL 2020\n\n   Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti\n   \n* [*\"OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03147) ([code](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)) - EMNLP 2020\n\n  Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti\n   \n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n   \n* [*\"Multi-Grained Dependency Graph Neural Network for Chinese Open Information Extraction\"*](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n\n### Canonicalization of OIE\n\n* *[\"Canonicalizing Open Knowledge Bases\"](https:\u002F\u002Fsuchanek.name\u002Fwork\u002Fpublications\u002Fcikm2014.pdf)* - CIKM 2014\n\n  Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek\n  \n* *[\"CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3186030)* - WWW 2018 ([code](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi))\n  \n  Shikhar Vashishth, Prince Jain, Partha Talukdar\n  \n* *[\"Towards Practical Open Knowledge Base Canonicalization\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271707)* - CIKM 2018\n\n   Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, Pengcheng Yin\n  \n* *[\"CaRe: Open Knowledge Graph Embeddings\"](http:\u002F\u002Ftalukdar.net\u002Fpapers\u002FCaRe_EMNLP2019.pdf)* - EMNLP 2019 ([code](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FCaRE))\n\n   Swapnil Gupta, Sreyash Kenkre, Partha Talukdar\n   \n* *[\"Canonicalization of Open Knowledge Bases with Side Information from the Source Text\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8731346)* - ICDE 2019\n\n   Xueling Lin, Lei Chen\n   \n* *[\"MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-62005-9_23)* - WISE 2020\n\n   Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen\n   \n* [*\"Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09610.pdf) - CoRR 2020\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n* [*\"Open Knowledge Graphs Canonicalization using Variational Autoencoders\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.811\u002F) - EMNLP 2021 ([code](https:\u002F\u002Fgithub.com\u002FIBM\u002FOpen-KG-canonicalization))\n\n    Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo\n   \n* [*\"Joint Open Knowledge Base Canonicalization and Linking\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3452776) - SIGMOD 2021\n\n   \tYinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan\n    \n* [*\"CaSIE: Canonicalize and Informative Selection of the OpenIE system\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9458825) - ICDE 2021\n\n   Hao Xin, Xueling Lin, Lei Chen\n   \n* [*\"Multi-View Clustering for Open Knowledge Base Canonicalization\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3534678.3539449) - KDD 2022\n\n   Wei Shen, Yang Yang, Yinan Liu\n\n\n## Slides\n* [\\[pdf\\] *\"Compact Open Information Extraction on Large Corpora\"*](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002FFiles_People\u002FResearchers\u002Fgashteovski\u002Foie_nec_labs_gashteovski.pdf). Talk by Kiril Gashteovski given at NEC Labs Europe GmbH, 2019.\n* [\\[pdf\\] *\"(Information Extraction) Lecture 10 – Ontological and Open IE\"*](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002Finformation_extraction_2015_lecture\u002F10_ontological_and_open_IE.pdf): A lecture on Open IE, which is part of the course [\"Information Extraction\"](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002Finformation_extraction_2018_lecture\u002F), by [Prof. Dr. Alexander Fraser](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002F), from LMU München\n* Open IE Tutorial: [Open Information Extraction for QA](https:\u002F\u002Fwww.slideshare.net\u002Fandrenfreitas\u002Fopen-ie-tutorial-2018) by [André Freitas](http:\u002F\u002Fandrefreitas.org\u002F). Tutorial was presented on OKBQA 2018\n* [\\[pdf\\] \"Chinese Open Relation Extraction and Knowledge Base Establishment\"](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf), 2018\n* [\\[pdf\\] *\"Brief Introduction and Review of Open Information Extraction (Open-IE) Systems\"*](https:\u002F\u002Fece.umd.edu\u002F~smiran\u002FOpenIE.pdf). Project Presentation by Sina Miran.\n* [\\[pdf\\] *\"Open Information Extraction Systems and Downstream Applications\"*](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fijcai16-earlycareer.pdf) by [Prof. Mausam](http:\u002F\u002Fwww.cse.iitd.ernet.in\u002F~mausam\u002F). The talk was presented at [IJCAI 2016](http:\u002F\u002Fijcai-16.org\u002F)\n* [\\[pptx\\] *\"Open Information Extraction from the Web\"*](https:\u002F\u002Fakbcwekex2012.files.wordpress.com\u002F2012\u002F06\u002Fslides-oren.pptx), presented by [Prof. Oren Etzioni](https:\u002F\u002Fallenai.org\u002Fteam\u002Forene\u002F). The tutorial was presented at [AKBC-WEKEX 2012](https:\u002F\u002Fakbcwekex2012.wordpress.com\u002F)\n* [\\[pdf\\] *\"ClausIE: Clause-Based Open Information Extraction\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro13clausie-slides.pdf) by [Luciano del Corro](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002F). \n* [\\[pdf\\] *\"Open Information Extraction: the Second Generation\"*](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fcourses\u002Fcol864\u002Fspring2017\u002Fslides\u002F03-openie.pdf)\n* [\\[pdf\\] *\"Open Information Extraction: Where Are We Going?\"*](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002Ftalks\u002Ftalk_OIE.pdf) by [Claudio Delli Bovi](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002F), 2016\n* [\\[pdf\\] *\"An Informativeness Approach to Open Information Extraction Evaluation\"*](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf) by [William Léchelle](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002F), 2016 \n\n\n## Talks\n\n* [*\\[video\\] \"Open Information Extraction from the Web\"*](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=lMiLiPjGays&feature=youtu.be), by [Prof. Oren Etzioni](https:\u002F\u002Fallenai.org\u002Fteam\u002Forene\u002F), presented at [AKBC-WEKEX 2012](https:\u002F\u002Fakbcwekex2012.wordpress.com\u002F).\nSlides: [\\[pptx\\]](https:\u002F\u002Fakbcwekex2012.files.wordpress.com\u002F2012\u002F06\u002Fslides-oren.pptx)\n* [*\\[video\\] \"Open Information Extraction: Where Are We Going?\"*](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EhOF_AbDwcE), by [Claudio Delli Bovi](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002F). The talk was given at AI2 in 2016. [Slides \\[pdf\\]](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002Ftalks\u002Ftalk_OIE.pdf)\n* [*\\[video\\] \"Nested Propositions in Open Information Extraction\"*](https:\u002F\u002Fvimeo.com\u002F239245885) by Nikita Bhutani at EMNLP 2016\n* [*\\[video\\] \"Creating a Large Benchmark for Open Information Extraction\"*](https:\u002F\u002Fvimeo.com\u002F239251034) by Gabriel Stanovsky at EMNLP 2016  \n* [*\\[video\\] \"OpenCeres: When Open Information Extraction Meets the Semi-Structured Web\"*](https:\u002F\u002Fvimeo.com\u002F355837778) by Colin Lockard at NAACL 2019 [slides \\[pdf\\]](https:\u002F\u002Fhomes.cs.washington.edu\u002F~lockardc\u002FOpenCeres_NAACL_talk.pdf)\n\n## Code\n\n* MinIE: Open Information Extraction System\n  * [MinIE](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002Fminie): originally written in Java\n  * [Python wrapper for MinIE](https:\u002F\u002Fgithub.com\u002Fmmxgn\u002Fminiepy)\n  * [MinScIE](https:\u002F\u002Fgithub.com\u002Fgkiril\u002FMinSCIE) - an Open Information Extraction system which provides structured knowledge enriched with semantic information about citations (based on MinIE).\n  * [SalIE](https:\u002F\u002Fgithub.com\u002Fmponza\u002FSalIE) - Salient Open Information Extraction (based on MinIE)\n* ClausIE: Clause-based OIE\n  * [ClausIE](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fsoftware\u002Fclausie\u002F): originally written in Java\n  * [ClausIE (mavenized version)](https:\u002F\u002Fgithub.com\u002FIsaacChanghau\u002FClausIE)\n  * [ClausIEpy](https:\u002F\u002Fgithub.com\u002Fdrwiner\u002FClausIEpy): Python wrapper for ClausIE\n* OpenIE at IIT Delhi:\n  * [OpenIE6](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)\n  * [IMoJIE](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie): a BERT-based OpenIE system\n  * [OpenIE5](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FOpenIE-standalone)\n* OpenIE at UW:\n  * [OLLIE](http:\u002F\u002Fknowitall.github.io\u002Follie\u002F)\n  * [ReVerb](http:\u002F\u002Freverb.cs.washington.edu\u002F)\n* Stanford's OpenIE:\n  * [Stanford OpenIE](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fopenie.html): Stanford's OpenIE system.\n  * [Stanford OpenIE Spider](https:\u002F\u002Fgithub.com\u002Fliaoziyang\u002FOpenIE-Spider): Extract Information from WebCorpus using Stanford Open Information Extraction.\n  * [Python wrapper for Stanford OpenIE](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python): The unofficial cross-platform Python wrapper for the state-of-art information extraction library from Stanford University.\n* [Graphene:](https:\u002F\u002Fgithub.com\u002FLambda-3\u002FGraphene) OpenIE system containing coreference resolution, simplification and open relation extraction pipeline\n* [EXEMPLAR](https:\u002F\u002Fgithub.com\u002FU-Alberta\u002Fexemplar)\n* [DefIE:](https:\u002F\u002Fgithub.com\u002Fclaudio-db\u002FdefIE) Open information extraction from textual definitions\n* [ReMine:](https:\u002F\u002Fgithub.com\u002FGentleZhu\u002FReMine) Integrating Local and Global Cohesiveness for Open Information Extraction \n* OIE systems for languages other than English or cross-lingual systems:\n   * [Zhopenie - Chinese OIE](https:\u002F\u002Fgithub.com\u002Ftim5go\u002Fzhopenie): OIE system for **Chinese** language written in Python.\n   * [Open Relation Extraction for Chinese](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction): Knowledge triples extraction (entities and relations extraction) and knowledge base construction based on dependency syntax for open domain text (for **Chinese**)\n   * [Baaz](https:\u002F\u002Fgithub.com\u002Fsobhe\u002Fopenie): Open information extraction from **Persian** web (Python)\n   * [MT\u002FIE](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie): Cross-lingual Open IE. Attention-based sequence-to-sequence model for cross-lingual open IE. Written in Python\n   * [Relation Extraction on German Websites](https:\u002F\u002Fgithub.com\u002Ftabergma\u002Frelation-extraction): This repository holds a collection of three Open Information Extraction approaches for the **German** language\n   * [DptOIE:](https:\u002F\u002Fgithub.com\u002FFORMAS\u002FDptOIE) A **Portuguese** Open Information Extraction system based on Dependency Analysis\n   * [PragmaticOIE:](https:\u002F\u002Fgithub.com\u002FFORMAS\u002FPragmaticOIE) a rule-based approach to extract facts in **Portuguese** in a first pragmatic level\n* [CORE:](https:\u002F\u002Fgithub.com\u002Ffabiopetroni\u002FCORE) Context-Aware Open Relation Extraction with Factorization Machines\n* [CESI:](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi) Canonicalizing Open Knowledge Bases using Embeddings and Side Information\n* [IMPLIE:](https:\u002F\u002Fgithub.com\u002Fknowitall\u002Fimplie) IMPLIE (IMPLicit relation Information Extraction) is a program that extracts binary relations from English sentences where the relationship between the two entities is not explicitly stated in the text.\n* [Ranking:](https:\u002F\u002Fgithub.com\u002Fjzbjyb\u002Foie_rank) Iterative Rank-Aware Open IE (confidence score).\n\n\n## Data\n\nOIE output is used as a useful input in many other downstream tasks, such as question answering, event schema induction or generating inference rules. Moreover, OIE output can be used as a \"fuel\" to derive further resources. Here, the data is organized into two major categories: 1) OIE corpora; 2) Resources derived from OIE output.\n\n### OIE corpora\n\n* [OPIEC: An Open Information Extraction Corpus:](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F) the largest OIE corpus to date, containing more than 341M triples extracted from the entire English Wikipedia. Each triple from the corpus is composed of rich meta-data: each token from the subj \u002F obj \u002F rel along with NLP annotations (POS tag, NER tag, ...), provenance sentence along with the dependency parse, original (golden) left from Wikipedia, sentence order, space \u002F time, etc.\n* [\\[.gz\\] ReVerb extractions](http:\u002F\u002Freverb.cs.washington.edu\u002Freverb_clueweb_tuples-1.1.txt.gz): 15 million high-precision  OIE extractions (826MB compressed) from the OIE system ReVerb. The extractions were made from the [ClueWeb09 corpus](https:\u002F\u002Flemurproject.org\u002Fclueweb09\u002F). The data contains *(subject, relation, object)* triples, accompanied by a confidence score (estimating the likelihood of whether the triple was correctly  extracted) and provenance information (the link of the web-page where the triple was extracted from).\n* [ReVerb extractions (linked)](http:\u002F\u002Fknowitall.cs.washington.edu\u002Flinked_extractions\u002F): 3 million triples with linked argument (a subset of the 15 M high-precision ReVerb extractions). The links (to Freebase) are provided by an entity linker. The data fields are: *argument 1, relation phrase, argument 2, freebase ID for argument 1 link, corresponding freebase entity name, link score, link ambiguity score*\n* [PATTY](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fresearch\u002Fyago-naga\u002Fpatty\u002F): PATTY is a system that takes open relations between two arguments, structures them into relational synsets and then organizes the synsets into a taxonomy. This resource contains over 15M triples with disambiguated arguments (links to WikiPedia articles) and relation synset ID between them. Additionaly, the resource contains: 1) relation pattern synsets with type signatures; 2) relation pattern subsumptions; 3) relation paraphrases; 4) evaluation data;\n* [WiseNet (1.0 and 2.0)](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F): similarly as PATTY, WiseNet 1.0\u002F2.0 is a source containing of OIE triples, where the arguments are disambiguated and the open relations are organized into relation synsets and then taxonomized. One of the main differences between PATTY and WiseNet is that WiseNet contains \"golden links\" for the arguments (annotated by humans) by keeping the original links from the WikiPedia articles.\n* [KB-Unify](http:\u002F\u002Flcl.uniroma1.it\u002Fkb-unify\u002F): KB-Unify takes as an input several OIE corpora and unifies them into a single disambiguated OIE repository. The open relations are organized into relational synsets and the arguments are disambiguated with BabelFy. \n\n### Resources derived from OIE output\n\n* [Functional relations](http:\u002F\u002Fknowitall.cs.washington.edu\u002Fleibniz\u002F): 10K Functional relations. This resource comes from the paper [*\"Identifying Functional Relations in Web Text\"*](http:\u002F\u002Fknowitall.cs.washington.edu\u002Fleibniz\u002Fpaper.pdf), published on EMNLP 2010.\n* [Entailment rules](http:\u002F\u002Fu.cs.biu.ac.il\u002F~nlp\u002Fresources\u002Fdownloads\u002Fpredicative-entailment-rules-learned-using-local-and-global-algorithms\u002F): 10M predicative entailment rules learned using local and global algorithms. From the documentation: \n  \"This resource of predicative entailment rules contains three resources in two formats – shallow and syntactic. Resources are learned over the REVERB data set and using the local and algorithms described in Chapter 5 of Jonathan Berant’s thesis (which is part of the package).\"\n* [Entailment rules](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fkglr): 36K high precision entailment rules (data and code). The resource is the result of the work of Prachi Jain and Mausam [*\"Knowledge-Guided Linguistic Rewrites for Inference Rule Verification\"*](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fpapers\u002Fnaacl16b.pdf) published on NAACL-HLT, 2016.\n\n### PhD theses\n\n* [*\"Compact Open Information Extraction: Methods, Corpora, Analysis\"*](https:\u002F\u002Fmadoc.bib.uni-mannheim.de\u002F59813\u002F1\u002Fthesis-kiril-gashteovski-final.pdf) by Kiril Gashteovski, University of Mannheim, Germany, 2020\n\n* [*\"Constructing Lexicons of Relational Phrases\"*](https:\u002F\u002Fpublikationen.sulb.uni-saarland.de\u002Fbitstream\u002F20.500.11880\u002F26789\u002F1\u002Fadam_grycner.pdf) by Adam Grycner, University of Saarland, Germany, 2017\n\n* [*\"Methods for open information extraction and sense disambiguation on natural language text\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro-thesis.pdf) by Luciano Del Corro, University of Saarland, Germany, 2016\n\n* [*\"Automated Knowledge Base Extension Using Open Information\"*](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F40469\u002F1\u002Fdutta.dissertation.pdf) by Arnab Kumar Dutta, University of Mannheim, Germany, 2015\n\n* [*\"Exploiting Knowledge in Unsupervised Open Information Extraction\"*](https:\u002F\u002Fsearch.proquest.com\u002Fdocview\u002F1372164047?pq-origsite=gscholar) by Yuval Merhav, Illinois Institute of Technology, USA, 2012\n\n* [*\"Open Information Extraction for the Web\"*](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fbanko-thesis.pdf) by Michele Banko, University of Washington, USA, 2009\n\n### Demos\n* [ClausIE:](https:\u002F\u002Fgate.d5.mpi-inf.mpg.de\u002FClausIEGate\u002FClausIEGate\u002F) Demo for ClausIE, an OIE system.\n* [Fact retrieval:](https:\u002F\u002Fopenie.allenai.org\u002F) Fact retrieval with OpenIE on large corpora.\n","# 开放信息抽取（OIE）资源\n\n一个精选的开放信息抽取（Open Information Extraction，简称 OIE）资源列表：研究论文、代码、数据、应用等。该列表不仅限于纯粹的开放信息抽取系统，还包括与 OIE 高度相关的工作，例如对开放关系进行分类以及在下游应用中使用 OIE。\n\n## 目录\n\n* [OIE 简介](#oie-简介)\n* [按时间顺序排列的论文](#按时间顺序排列的论文)\n  * [2006](#2006)\n  * [2007](#2007)\n  * [2008](#2008)\n  * [2009](#2009)\n  * [2010](#2010)\n  * [2011](#2011)\n  * [2012](#2012)\n  * [2013](#2013)\n  * [2014](#2014)\n  * [2015](#2015)\n  * [2016](#2016)\n  * [2017](#2017)\n  * [2018](#2018)\n  * [2019](#2019)\n  * [2020](#2020)\n  * [2021](#2021)\n  * [2022](#2022)\n* [按类别分组的论文](#按类别分组的论文)\n  * [综述](#综述)\n  * [评估](#评估)\n  * [用于下游应用的 OIE](#用于下游应用的-oie)\n    * [问答系统](#问答系统)\n    * [槽位填充](#槽位填充)\n    * [事件抽取](#事件抽取)\n    * [文本摘要](#文本摘要)\n    * [知识库填充](#知识库填充)\n    * [知识库构建](#知识库构建)\n    * [实体链接](#实体链接)\n    * [关系链接](#关系链接)\n    * [开放链接预测](#开放链接预测)\n    * [关系抽取](#关系抽取)\n    * [实体关联](#实体关联)\n    * [故事理解](#故事理解)\n    * [文本生成](#文本生成)\n    * [视频定位](#视频定位)\n  * [不同语言中的 OIE](#不同语言中的-oie)\n    * [德语 OIE 系统](#德语-oie-系统)\n    * [葡萄牙语 OIE 系统](#葡萄牙语-oie-系统)\n    * [西班牙语 OIE 系统](#西班牙语-oie-系统)\n    * [中文 OIE 系统](#中文-oie-系统)\n    * [波斯语 OIE 系统](#波斯语-oie-系统)\n    * [意大利语 OIE 系统](#意大利语-oie-系统)\n    * [印尼语 OIE 系统](#印尼语-oie-系统)\n    * [希腊语 OIE 系统](#希腊语-oie-系统)\n  * [监督式 OIE](#监督式-oie)\n  * [OIE 的规范化](#oie-的规范化)\n* [幻灯片](#幻灯片)\n* [演讲](#演讲)\n* [代码](#代码)\n* [数据](#数据)\n  * [OIE 语料库](#oie-语料库)\n  * [从 OIE 输出衍生的资源](#从-oie-输出衍生的资源)\n* [博士论文](#博士论文)\n* [演示](#演示)\n\n## OIE 简介\n\n开放信息抽取（OIE）系统旨在以无监督的方式从未结构化文本中提取未见过的关系及其参数。在其最简单的形式中，给定一个自然语言句子，它们会以三元组的形式提取信息，三元组由主语（S）、关系（R）和宾语（O）组成。\n\n假设我们有以下输入句子：\n\n    AMD，总部位于美国，是一家技术公司。\n\n一个 OIE 系统的目标是做出以下提取：\n\n    (\"AMD\"; \"is based in\"; \"U.S.\")\n    (\"AMD\"; \"is\"; \"technology company\")\n\n## 按时间顺序排列的论文\n\n### 2006\n\n* *[\"Machine Reading\"](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FSymposia\u002FSpring\u002F2007\u002FSS-07-06\u002FSS07-06-001.pdf)* - AAAI 2006\n\n  Oren Etzioni, Michele Banko, Michael J. Cafarella\n\n### 2007\n* *[\"Open Information Extraction from the Web\"](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FIJCAI\u002F2007\u002FIJCAI07-429.pdf)* - IJCAI 2007\n  \n  Michele Banko,  Michael J. Cafarella, Stephen Soderland, Matthew Broadhead, Oren Etzioni\n  \n* *[\"Unsupervised Resolution of Objects and Relations on the Web\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fobject_identification_camera_ready_4.pdf)* - NAACL 2007\n\n  Alexander Yates, Oren Etzioni\n  \n* *[\"TextRunner: Open Information Extraction on the Web\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002Fp25-yates.pdf)* -  HLT-NAACL 2007\n\n  Alexander Yates, Michele Banko, Matthew Broadhead, Michael J. Cafarella, Oren Etzioni, Stephen Soderland\n  \n### 2008\n* *[\"The Tradeoffs between Open and Traditional Relation Extraction\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Facl08.pdf)* - ACL 2008\n\n  Michele Banko, Oren Etzioni\n\n* *[\"Open Knowledge Extraction through Compositional Language Processing\"](https:\u002F\u002Fwww.cs.rochester.edu\u002F~schubert\u002Fpapers\u002Fopen-knowledge-step08.pdf)* - STEP 2008\n\n  Benjamin Van Durme, Lenhart K. Schubert\n\n* *[\"Open Information Extraction from the Web\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=1409378)* - Commun. ACM 2008\n\n  Oren Etzioni, Michele Banko, Stephen Soderland, Daniel S. Weld\n  \n### 2009\n\n* *[\"Using Wikipedia to Bootstrap Open Information Extraction\"](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.143.4369&rep=rep1&type=pdf)* - SIGMOD 2009\n  \t\n    Daniel S. Weld, Raphael Hoffmann, Fei Wu\n    \n### 2010\n\n* *[\"Open Information Extraction Using Wikipedia\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP10-1013)* - ACL 2010\n\n  Fei Wu, Daniel S. Weld\n  \n* *[\"Identifying Functional Relations in Web Text\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Femnlp10.pdf)* - EMNLP 2010\n  \n  Thomas Lin, Mausam, Oren Etzioni\n\n* *[\"Adapting Open Information Extraction to Domain-Specific Relations\"](https:\u002F\u002Fwww.aaai.org\u002Fojs\u002Findex.php\u002Faimagazine\u002Farticle\u002Fview\u002F2305)* -  AI Magazine (31), 2010\n\n  Stephen Soderland, Brendan Roof, Bo Qin, Shi Xu, Mausam, Oren Etzioni \n  \n### 2011\n\n* *[\"Open Information Extraction: The Second Generation\"](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fetzioni-ijcai2011.pdf)* -  IJCAI 2011 ([slides](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fcourses\u002Fcol864\u002Fspring2017\u002Fslides\u002F03-openie.pdf))\n  \n  Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland, Mausam\n  \n* *[\"Identifying Relations for Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD11-1142)* - EMNLP 2011 [(resources (code, data)](http:\u002F\u002Freverb.cs.washington.edu\u002F))\n\n  Anthony Fader, Stephen Soderland, Oren Etzioni\n  \n* *[\"Filtering and Clustering Relations for Unsupervised Information Extraction in Open Domain\"](https:\u002F\u002Fperso.limsi.fr\u002Fbg\u002Ffichiers\u002F2011\u002Fcikm0874-wang.pdf)* - CIKM 2011\n\n  Wei Wang, Romaric Besançon, Olivier Ferret, Brigitte Grau\n\n* *[\"An Analysis of Open Information Extraction based on Semantic Role Labeling\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fkcap11.pdf)* - K-CAP 2011\n\n  Janara Christensen, Mausam, Stephen Soderland, Oren Etzioni\n\n### 2012\n\n* *[\"开放语言学习用于信息抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1048)* - EMNLP-CoNLL 2012 ([资源（代码、数据、二进制文件）](http:\u002F\u002Fknowitall.github.io\u002Follie\u002F))\n\n  Mausam, Michael Schmitz, Stephen Soderland, Robert Bart, Oren Etzioni\n  \n* *[\"PATTY：基于语义类型的分类模式的分类法\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1104)* - EMNLP-CoNLL 2012\n\n  Ndapandula Nakashole, Gerhard Weikum, Fabian M. Suchanek\n  \n* *[\"大规模无监督关系抽取的集成语义\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD12-1094)* - EMNLP-CoNLL 2012\n\n  Bonan Min, Shuming Shi, Ralph Grishman, Chin-Yew Lin\n  \n* *[\"WiSeNet：构建基于维基百科的带本体化关系的语义网络\"](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~moro\u002FMoroNavigli_CIKM12.pdf)* - CIKM 2012 ([资源](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F))\n\n  Andrea Moro, Roberto Navigli\n  \n* *[\"基于实体谓词对检测的SOV语言的开放信息抽取\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC12-3038)* - COLING 2012\n\n  Woong-Ki Lee, Yeon-Su Lee, Hyoung-Gyu Lee, Won-Ho Ryu, Hae-Chang Rim\n  \n* *[\"开放信息抽取的加权方案\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN12-2011)* - HLT-NAACL 2012\n\n  Yuval Merhav\n\n* *[\"基于依存关系的开放信息抽取\"](http:\u002F\u002Fwww.anthology.aclweb.org\u002FW\u002FW12\u002FW12-0702.pdf)* - ACL 2012 自然语言处理中的无监督与半监督学习联合研讨会\n\n  Pablo Gamallo, Marcos Garcia\n  \n* *[\"KrakeN：开放信息抽取中的n元事实\"](http:\u002F\u002Fwing.comp.nus.edu.sg\u002F~antho\u002FW\u002FW12\u002FW12-3010.pdf)* - AKBC-WEKEX@NAACL-HLT 2012\n\n  Alan Akbik, Alexander Löser\n  \n* *[\"使用逐级下降规则改进非正式Web文档的开放信息抽取\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-642-32541-0_14)* - PKAW 2012\n\n  Myung Hee Kim, Paul Compton\n  \n### 2013\n\n* *[\"ClausIE：基于子句的开放信息抽取\"](http:\u002F\u002Fresources.mpi-inf.mpg.de\u002Fd5\u002Fclausie\u002Fclausie-www13.pdf)* - WWW 2013 ([幻灯片](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro13clausie-slides.pdf), [代码](http:\u002F\u002Fresources.mpi-inf.mpg.de\u002Fd5\u002Fclausie\u002Fclausie-0-0-1.zip), [所有资源](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fsoftware\u002Fclausie\u002F))\n\n  Luciano Del Corro, Rainer Gemulla\n  \n* *[\"将句法和语义分析整合到开放信息抽取范式中\"](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~moro\u002FMoroNavigli_IJCAI13.pdf)* - IJCAI 2013 ([资源](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F))\n\n  Andrea Moro, Roberto Navigli\n\n* *[\"开放关系抽取的有效性与效率\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD13-1043)* - EMNLP 2013 ([代码](https:\u002F\u002Fgithub.com\u002FU-Alberta\u002Fexemplar))\n\n  Filipe de Sá Mesquita, Jordan Schmidek, Denilson Barbosa\n  \n* *[\"使用树核函数进行开放信息抽取\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN13-1107)* - HLT-NAACL 2013\n \n  Ying Xu, Mi-Young Kim, Kevin Quinn, Randy Goebel, Denilson Barbosa\n  \n* *[\"使用矩阵分解和通用模式的关系抽取\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN13-1008)* - HLT-NAACL 2013 \n\n  Sebastian Riedel, Limin Yao, Andrew McCallum, Benjamin M. Marlin\n  \n* *[\"通过上下文句子分解进行开放信息抽取\"](http:\u002F\u002Fad-publications.cs.uni-freiburg.de\u002FICSC_csdie_BH_2013.pdf)* - ICSC 2013\n  \n  Hannah Bast, Elmar Haussmann\n  \n* *[\"整合开放和封闭信息抽取：挑战与第一步\"](http:\u002F\u002Fceur-ws.org\u002FVol-1064\u002FDutta_Integrating.pdf)* - NLP-DBPEDIA@ISWC 2013\n\n  Arnab Dutta, Christian Meilicke, Mathias Niepert, Simone Paolo Ponzetto\n  \n* *[\"在3小时内从开放信息抽取到KBP关系\"](https:\u002F\u002Fpdfs.semanticscholar.org\u002Fd431\u002F81fa9af5440360d4055e1ce7ddaaa6e82d77.pdf)* - TAC 2013\n\n  Stephen Soderland, John Gilmer, Robert Bart, Oren Etzioni, Daniel S. Weld\n  \n### 2014\n\n* *[\"ReNoun：名词属性的事实抽取\"](http:\u002F\u002Femnlp2014.org\u002Fpapers\u002Fpdf\u002FEMNLP2014038.pdf)* - EMNLP 2014\n  \t\n  Mohamed Yahya, Steven Whang, Rahul Gupta, Alon Y. Halevy\n    \n* *[\"ZORE：基于句法的中文开放关系抽取系统\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD14-1201)* - EMNLP 2014\n\n  Likun Qiu, Yue Zhang\n  \n* *[\"规范化开放知识库\"](https:\u002F\u002Fsuchanek.name\u002Fwork\u002Fpublications\u002Fcikm2014.pdf)* - CIKM 2014\n\n  Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek\n  \n* *[\"针对开放IE命题的聚焦蕴含图\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW14-1610)* - CoNLL 2014\n\n  Omer Levy, Ido Dagan, Jacob Goldberger\n\n* *[\"通过基于名词的关系提升开放信息抽取\"](https:\u002F\u002Fpdfs.semanticscholar.org\u002F570c\u002Fce7b24c51f75da091b515baddce567128680.pdf)* - LREC 2014\n\n  Clarissa Castellã Xavier, Vera Lúcia Strube de Lima\n\n* *[\"通过句子重构改进开放关系抽取\"](http:\u002F\u002Fwww.lrec-conf.org\u002Fproceedings\u002Flrec2014\u002Fpdf\u002F1038_Paper.pdf)* - LREC 2014\n\n  Jordan Schmidek, Denilson Barbosa\n\n* *[\"通过简单推理获取更具信息量的开放信息抽取\"](http:\u002F\u002Fad-publications.informatik.uni-freiburg.de\u002FECIR_csdie-inf_BH_2014.pdf)* - ECIR 2014\n\n  Hannah Bast, Elmar Haussmann\n  \n* *[\"从开放信息抽取系统中语义化三元组\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F36881\u002F1\u002FFAIA264-0111.pdf)* - STAIRS 2014\n\n  Arnab Dutta, Christian Meilicke, Heiner Stuckenschmidt\n\n* *[\"面向开放信息抽取的人物实体以实体为中心的共指消解\"](http:\u002F\u002Fwww.taln.upf.edu\u002Fpages\u002Fsepln2014\u002Ffull_papers\u002Fedited_paper_30.pdf)* - Procesamiento del Lenguaje Natural (2014)\n\n  Marcos García, Pablo Gamallo\n  \n* *[\"基于句法约束的西班牙语开放信息抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP14-3011.pdf)* - ACL（学生研究研讨会）(2014)\n\n  Alisa Zhila, Alexander Gelbukh\n\n### 2015\n\n* *[\"利用语言结构进行开放域信息抽取\"](https:\u002F\u002Fnlp.stanford.edu\u002Fpubs\u002F2015angeli-openie.pdf)* - ACL 2015 ([代码 (Java)](https:\u002F\u002Fstanfordnlp.github.io\u002FCoreNLP\u002Fopenie.html), [代码 (Python)](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python))\n\n  Gabor Angeli, Melvin Jose Johnson Premkumar, Christopher D. Manning\n\n* *[\"将开放信息抽取作为语义任务的中间结构\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP15-2050)* - ACL 2015\n\n  Gabriel Stanovsky, Ido Dagan, Mausam\n  \n* *[\"通过深层句法和语义分析从文本定义中进行大规模信息抽取\"](https:\u002F\u002Ftransacl.org\u002Fojs\u002Findex.php\u002Ftacl\u002Farticle\u002Fview\u002F660)* - TACL 2015 ([资源](http:\u002F\u002Flcl.uniroma1.it\u002Fdefie\u002F))\n\n  Claudio Delli Bovi, Luca Telesca, Roberto Navigli\n  \n* *[\"为开放信息抽取推断二元关系模式\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD15-1065)* - EMNLP 2015\n\n  Kangqi Luo, Xusheng Luo, Kenny Qili Zhu\n  \n* *[\"通过词义嵌入和消歧实现知识库统一\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD15-1084)* - EMNLP 2015 ([资源](http:\u002F\u002Flcl.uniroma1.it\u002Fkb-unify\u002F))\n\n  Claudio Delli Bovi, Luis Espinosa Anke, Roberto Navigli\n  \n* *[\"CORE: 使用因子分解机进行上下文感知的开放关系抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD15-1204)* - EMNLP 2015 ([代码](https:\u002F\u002Fgithub.com\u002Ffabiopetroni\u002FCORE))\n\n  Fabio Petroni, Luciano Del Corro, Rainer Gemulla\n  \n* [*\"使用跨语言投影的多语言开放关系抽取\"*](https:\u002F\u002Fstatic.googleusercontent.com\u002Fmedia\u002Fresearch.google.com\u002Fen\u002F\u002Fpubs\u002Farchive\u002F43449.pdf) - HLT-NAACL 2015\n\n  Manaal Faruqui, Shankar Kumar\n  \n* [*\"用开放信息丰富结构化知识\"*](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F38861\u002F1\u002Fp267.pdf) - WWW 2015\n\n  Arnab Dutta, Christian Meilicke, Heiner Stuckenschmidt\n  \n* *[\"SRDF: 使用单例属性的韩语开放信息抽取\"](http:\u002F\u002Fceur-ws.org\u002FVol-1486\u002Fpaper_55.pdf)* - ISWC 2015\n\n  Sangha Nam, YoungGyun Hahm, Sejin Nam, Key-Sun Choi\n\n* *[\"多语言开放信息抽取\"](https:\u002F\u002Fgramatica.usc.es\u002F~gamallo\u002Fartigos-web\u002FEPIA2015.pdf)* - EPIA 2015\n\n  Pablo Gamallo, Marcos García\n  \n* *[\"基于词汇语义的开放信息抽取\"](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1186\u002Fs13173-015-0023-2)* - J. Braz. Comp. Soc. 21 2015\n\n  Clarissa Castellã Xavier, Vera Lúcia Strube de Lima, Marlo Souza\n  \n### 2016\n\n* *[\"开放信息抽取中的嵌套命题\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1006)* - EMNLP 2016 ([演讲](https:\u002F\u002Fvimeo.com\u002F239245885))\n\n  Nikita Bhutani, H. V. Jagadish, Dragomir R. Radev\n\n* *[\"创建一个大型开放信息抽取基准\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1252)* - EMNLP 2016 ([代码](https:\u002F\u002Fgithub.com\u002FgabrielStanovsky\u002Foie-benchmark), [演讲](https:\u002F\u002Fvimeo.com\u002F239251034))\n\n  Gabriel Stanovsky, Ido Dagan\n  \n* *[\"将开放信息抽取系统从英语移植到德语\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1086)* - EMNLP 2016 ([代码](https:\u002F\u002Fgithub.com\u002FUKPLab\u002Fprops-de))\n\n  Tobias Falke, Gabriel Stanovsky, Iryna Gurevych, Ido Dagan\n  \n* *[\"使用侧信息的张量分解进行关系模式归纳\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD16-1040)* - EMNLP 2016 \n\n  Madhav Nimishakavi, Uday Singh Saini, Partha P. Talukdar\n  \n* *[\"开放信息抽取系统及其下游应用\"](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F604.pdf)* - IJCAI 2016\n\n  Mausam\n  \n* *[\"名词开放信息抽取中的居民名与复合关系名词\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fakbc16.pdf)* - AKBC@NAACL-HLT 2016\n\n  Harinder Pal, Mausam\n  \n* *[\"一种基于规则的级联有限状态转换器开放信息抽取方法\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-31750-2_26)* - PAKDD 2016\n\n  Hailun Lin, Yuanzhuo Wang, Peng Zhang, Weiping Wang, Yinliang Yue, Zheng Lin\n\n* *[\"通过PropS从语法中获取更多信息\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.01648.pdf)* - CoRR (2016)\n\n  Gabriel Stanovsky, Jessica Ficler, Ido Dagan, Yoav Goldberg\n\n* *[\"改进开放信息抽取以用于语义网任务\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-662-49521-6_6)* -  Trans. Computational Collective Intelligence 21, 2016\n\n  Cheikh Kacfah Emani, Catarina Ferreira Da Silva, Bruno Fiés, Parisa Ghodous\n  \n* *[\"一种开放信息抽取评估的信息性方法\"](http:\u002F\u002Frali.iro.umontreal.ca\u002Frali\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublis\u002FAn_informativeness_approach_to_Open_IE_evaluation%5B1%5D.pdf)* - CICLing 2016 ([幻灯片](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf), [代码 + 数据](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fdata\u002FCICLing_092.zip))\n\n  William Léchelle, Philippe Langlais\n\n### 2017\n\n* *[\"MinIE: Minimizing Facts in Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD17-1278)* - EMNLP 2017 ([代码](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002Fminie), [海报](https:\u002F\u002Fdws.informatik.uni-mannheim.de\u002Ffileadmin\u002Flehrstuehle\u002Fpi1\u002Fpeople\u002Frgemulla\u002Fpublications\u002Fgashteovski17minie-poster.pdf), [所有资源](https:\u002F\u002Fdws.informatik.uni-mannheim.de\u002Fen\u002Fresources\u002Fsoftware\u002Fminie\u002F))\n\n  Kiril Gashteovski, Rainer Gemulla, Luciano Del Corro\n  \n* *[\"Answering Complex Questions Using Open Information Extraction\"](http:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002FTupleInf_ACL17.pdf)* - ACL 2017\n\n  Tushar Khot, Ashish Sabharwal, Peter Clark\n  \n* *[\"Pocket Knowledge Base Population\"](https:\u002F\u002Fwww.cs.jhu.edu\u002F~mdredze\u002Fpublications\u002F2017_acl_pocket_kb.pdf)* - ACL 2017\n  \n  Travis Wolfe, Mark Dredze, Benjamin Van Durme\n  \n* *[\"Bootstrapping for Numerical Open IE\"](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Facl17.pdf)* - ACL 2017\n\n  Swarnadeep Saha, Harinder Pal, Mausam\n\n* *[\"MT\u002FIE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FE17-2011)* - EACL 2017 ([代码](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie))\n  \t\n  Kevin Duh, Benjamin Van Durme, Sheng Zhang\n  \n* *[Open Relation Extraction for Support Passage Retrieval: Merit and Open Issues\"](https:\u002F\u002Fwww.cs.unh.edu\u002F~dietz\u002Fappendix\u002Fopenie4ir\u002Fkadry-dietz-sigir2017-open-relation-extraction-for-support-passage-retrieval.pdf)* - SIGIR 2017\n\n  Amina Kadry, Laura Dietz\n    \n* *[\"Syntactic Representation Learning for Open Information Extraction on Web\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3041021.3054266)* - WWW 2017\n\n  Chengsen Ru, Jintao Tang, Shasha Li, Ting Wang\n    \n* *[\"MetaPAD: Meta Pattern Discovery from Massive Text Corpora\"](http:\u002F\u002Fwww.meng-jiang.com\u002Fpubs\u002Fmetapad-kdd17\u002Fmetapad-kdd17-paper.pdf)* ([代码](https:\u002F\u002Fgithub.com\u002Fmjiang89\u002FMetaPAD))- KDD 2017\n\n  Meng Jiang, Jingbo Shang, Taylor Cassidy, Xiang Ren, Lance M. Kaplan, Timothy P. Hanratty, Jiawei Han\n  \n* *[\"RelVis: Benchmarking OpenIE Systems\"](http:\u002F\u002Fceur-ws.org\u002FVol-1963\u002Fpaper527.pdf)* - ISWC 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n  \n* *[\"A Consolidated Open Knowledge Representation for Multiple Texts\"](https:\u002F\u002Faclanthology.org\u002FW17-0902.pdf)* -  LSDSem@EACL 2017\n\n  Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martínez-Cámara, Iryna Gurevych, Ido Dagan\n\n* *[\"Open Relation Extraction and Grounding\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FI17-1086)* - IJCNLP 2017\n\n  Dian Yu, Lifu Huang, Heng Ji\n  \n* *[\"Selective Decoding for Cross-lingual Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FI17-1084)* - IJCNLP(1) 2017\n\n  Sheng Zhang, Kevin Duh, Benjamin Van Durme\n\n* *[\"An assessment of open relation extraction systems for the semantic web\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306437916304999)* - Inf. Syst. 71, 2017\n\n  Amal Zouaq, Michel Gagnon, Ludovic Jean-Louis\n  \n* *[\"An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-6944)* - IWCS 2017\n\n  Sheng Zhang, Rachel Rudinger, Benjamin Van Durme\n  \n* *[\"Discovering Relational Phrases for Qualia Roles Through Open Information Extraction\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-69548-8_6)* - KESW 2017\n\n  Giovanni Siragusa, Valentina Leone, Luigi Di Caro, Claudio Schifanella\n  \n* *[\"Open Relation Extraction Based on Core Dependency Phrase Clustering\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8005507)* - DSC 2017\n\n  Chengsen Ru, Shasha Li, Jintao Tang, Yi Gao, Ting Wang  \n  \n* *[\"Analysing Errors of Open Information Extraction Systems\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-5402)* - Workshop on Building Linguistically Generalizable NLP Systems @ EMNLP 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n\n### 2018\n\n* *[\"Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002F2018_Logician_A_Unified_End-to-End_Neural_Approach_for_open_domain_IE(1).pdf)* - WSDM 2018\n\n  孙明明，李旭，王欣，范淼，冯越，李平\n\n* *[\"Assertion-Based QA With Question-Aware Open Information Extraction\"](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002Fdownload\u002F16705\u002F16170)* - AAAI 2018\n  \t\n  颜昭，唐都钰，段楠，刘树杰，王文迪，蒋大新，周明，李舟军\n  \n* *[\"Neural Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FP18-2065)* - ACL 2018\n\n  崔磊，魏富如，周明\n  \n* *[\"Supervised Open Information Extraction\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN18-1081)* - NAACL-HLT 2018\n  \t\n  Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan\n  \n* [*\"Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD18-1236) - EMNLP 2018\n\n   孙明明，李旭，李平\n  \n* *[\"Open Information Extraction from Conjunctive Sentences\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1194)* - COLING 2018\n\n  Swarnadeep Saha, Mausam\n  \n* *[\"Graphene: Semantically-Linked Propositions in Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1195)* - COLING 2018 ([code](https:\u002F\u002Fgithub.com\u002FLambda-3\u002FGraphene), [documentation](http:\u002F\u002Flambda3.org\u002FGraphene\u002F))\n\n  Matthias Cetto, Christina Niklaus, André Freitas, Siegfried Handschuh\n  \n* *[\"Open Information Extraction on Scientific Text: An Evaluation\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1289)* - COLING 2018\n  \n  Paul T. Groth, Michael Lauruhn, Antony Scerri, Ron Daniel\n  \n* *[\"A Survey on Open Information Extraction\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1326)* - COLING 2018\n\n  Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh\n  \n* *[\"StuffIE: Semantic Tagging of Unlabeled Facets Using Fine-Grained Information Extraction\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271812)* - CIKM 2018\n\n  Radityo Eko Prasojo, Mouna Kacimi, Werner Nutt\n  \n* *[\"Towards Practical Open Knowledge Base Canonicalization\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271707)* - CIKM 2018\n\n   吴天轩，吴志勇，高斌，尹鹏程\n  \n* *[\"Open Information Extraction with Global Structure Constraints\"](http:\u002F\u002Fwww-bcf.usc.edu\u002F~xiangren\u002Fwww18_poster.pdf)* - WWW 2018\n\n  Zhu Qi, Xiang Ren, Shang Jingbo, Zhang Yu, Frank F. Xu, Jiawei Han\n\n* *[\"CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3186030)* - WWW 2018 ([code](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi))\n  \n  Shikhar Vashishth, Prince Jain, Partha Talukdar\n\n* *[\"Revisiting the Task of Scoring Open IE Relations\"](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002Fsubmitted_to_LREC18.pdf)* ([poster](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2018-LREC-poster.pdf)) - LREC 2018\n\n  William Léchelle, Philippe Langlais\n  \n* *[\"Employing Semantic Context for Sparse Information Extraction Assessment\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3201407)* - TKDD 2018 ([resources](https:\u002F\u002Fgithub.com\u002Fpeipeilihfut\u002FAssessSparseIE))\n\n  李佩佩，王海勋，李洪松，伍新春\n  \n* *[\"Open Information Extraction with Meta-pattern Discovery in Biomedical Literature\"](https:\u002F\u002Fyuzhimanhua.github.io\u002Fpapers\u002Fbcb18.pdf)* - BCB 2018\n\n  王轩，张宇，李琦，陈音音，韩家炜\n  \n* *[\"Modeling and Summarizing News Events Using Semantic Triples\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-93417-4_33)* - ESWC 2018\n\n  Radityo Eko Prasojo, Mouna Kacimi, Werner Nutt\n  \n* *[\"Disambiguating Open IE: Identifying Semantic Similarity in Relation Extraction by Word Embeddings\"](https:\u002F\u002Fwww.springerprofessional.de\u002Fen\u002Fdisambiguating-open-ie-identifying-semantic-similarity-in-relati\u002F16122888)* - PROPOR 2018\n\n  Leandro M. P. Sanches, Victor S. Cardel, Larissa S. Machado, Marlo Souza, Laís do Nascimento Salvador\n  \n* *[\"Task-Oriented Evaluation of Dependency Parsing with Open Information Extraction\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-99722-3_8)* - PROPOR 2018\n\n  Pablo Gamallo, Marcos Garcia\n  \n* *[\"Challenges of an Annotation Task for Open Information Extraction in Portuguese\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-99722-3_7)* - PROPOR 2018\n\n  Rafael Glauber, Leandro Souza de Oliveira, Cleiton Fernando Lima Sena, Daniela Barreiro Claro, Marlo Souza\n  \n* *[\"A systematic mapping study on open information extraction\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418303932)* -  Expert Syst. Appl. 2018\n\n  Rafael Glauber, Daniela Barreiro Claro\n  \n* *[\"Self-training on refined clause patterns for relation extraction\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0306457316303259?dgcid=raven_sd_recommender_email)* - Inf. Process. Manage. 54(4): 686-706 (2018)\n\n  Duc-Thuan Vo, Ebrahim Bagheri\n  \n* *[\"Supervised Neural Models Revitalize the Open Relation Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.09408.pdf)* - CoRR 2018\n\n  贾胜斌，向阳，陈晓军\n  \n* *[\"Chinese Open Relation Extraction and Knowledge Base Establishment\"](https:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002F10094_Paper.pdf)* - ACM Trans. Asian & Low-Resource Lang. Inf. Process. 2018 ([slides](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf), [code](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction))\n\n  贾胜斌，鄂世佳，李茂贞，向阳\n  \n* *[Rule-based Indonesian Open Information Extraction\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8541293)* - ICAICTA 2018 \n\n  Ade Romadhony, Ayu Purwarianti, Dwi H. Widyantoro\n  \n* *[\"WiRe57 : A Fine-Grained Benchmark for Open Information Extraction\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.08962.pdf)* - CoRR 2018\n\n  William Léchelle, Fabrizio Gotti, Philippe Langlais\n  \n### 2019\n\n* *[\"OPIEC: An Open Information Extraction Corpus\"](https:\u002F\u002Fopenreview.net\u002Fpdf?id=HJxeGb5pTm)* - AKBC 2019 ([data + resources](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F), [code (data reading)](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002FOPIEC), [code (pipeline)](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002FOPIEC-pipeline))\n\n  Kiril Gashteovski, Sebastian Wanner, Sven Hertling, Samuel Broscheit, Rainer Gemulla\n  \n* *[\"MinScIE: Citation-centered Open Information Extraction\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F49216\u002F1\u002F_JCDL19Demo__MinScIE%20%284%29.pdf)* - JCDL 2019 ([code](https:\u002F\u002Fgithub.com\u002Fgkiril\u002FMinSCIE))\n\n  Anne Lauscher, Yide Song, Kiril Gashteovski\n  \n* *[\"EAL: A Toolkit and Dataset for Entity-Aspect Linking\"](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F49596\u002F1\u002FEAL.pdf)* - JCDL 2019 ([data](https:\u002F\u002Ffedericonanni.com\u002Feal-d\u002F), [code](https:\u002F\u002Fgithub.com\u002Fjinggz\u002FMaster-Thesis-EAL\u002Ftree\u002Fservice), [demo](http:\u002F\u002Ftools.dws.informatik.uni-mannheim.de\u002Feal))\n\n  Federico Nanni, Jingyi Zhang, Ferdinand Betz, Kiril Gashteovski\n\n* *[\"结合局部上下文和全局连贯性的开放信息抽取\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.09931.pdf)* - WSDM 2019 ([代码](https:\u002F\u002Fgithub.com\u002FGentleZhu\u002FReMine))\n\n  朱琪，任翔，商敬波，张宇，Ahmed El-Kishky，韩家炜\n\n* *[\"从问答对中进行开放信息抽取\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.00172.pdf)* - NAACL 2019\n\n  Nikita Bhutani, Yoshihiko Suhara, Wang-Chiew Tan, Alon Halevy 和 H V Jagadish\n  \n* *[\"OpenKI: 结合开放信息抽取与知识库的关系推理\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1083\u002F)* - NAACL 2019 ([数据](https:\u002F\u002Fgithub.com\u002Fzhangdongxu\u002Frelation-inference-naacl19)) \n\n  张东旭，Subhabrata Mukherjee，Colin Lockard，董欣 Luna，Andrew McCallum\n  \n* *[\"OpenCeres: 当开放信息抽取遇到半结构化网络\"](http:\u002F\u002Flunadong.com\u002Fpublication\u002FopenCeres_naacl.pdf)* - NAACL 2019 ([视频](https:\u002F\u002Fvimeo.com\u002F355837778), [幻灯片](https:\u002F\u002Fhomes.cs.washington.edu\u002F~lockardc\u002FOpenCeres_NAACL_talk.pdf), [数据](https:\u002F\u002Farchive.codeplex.com\u002F?p=swde))\n\n  Colin Lockard, Prashant Shiralkar 和 董欣 Luna \n  \n* *[\"通过迭代的排名感知学习改进开放信息抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1523)* - ACL 2019 ([代码](https:\u002F\u002Fgithub.com\u002Fjzbjyb\u002Foie_rank))\n\n   江正宝，尹鹏程 和 Graham Neubig\n   \n* *[\"开放关系抽取：从监督数据到无监督数据的关系知识迁移\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1021.pdf)* - EMNLP 2019\n\n   吴瑞东，姚远，韩旭，谢若冰，刘知远，林芬，林乐宇 和 孙茂松\n   \n* *[\"监督无监督的开放信息抽取模型\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1067.pdf)* - EMNLP 2019\n\n   Arpita Roy, Youngja Park, Taesung Lee 和 Shimei Pan\n   \n* *[\"CaRB: 一个众包的开放信息抽取基准\"](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002F\u002Fpapers\u002Femnlp19.pdf)* - EMNLP 2019 ([代码和数据](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FCaRB))\n\n   Sangnie Bhardwaj, Samarth Aggarwal 和 Mausam\n   \n* *[\"CaRe: 开放知识图谱嵌入\"](http:\u002F\u002Ftalukdar.net\u002Fpapers\u002FCaRe_EMNLP2019.pdf)* - EMNLP 2019 ([代码](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FCaRE))\n\n   Swapnil Gupta, Sreyash Kenkre, Partha Talukdar\n   \n* *[\"协作策略学习用于开放知识图谱推理\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1269.pdf)* - EMNLP 2019 ([代码](https:\u002F\u002Fgithub.com\u002FINK-USC\u002FCPL))\n \n   符聪，陈彤，瞿萌，Woojeong Jin，任翔\n   \n* *[\"多输入多输出序列标注用于联合抽取科学文本中的事实和条件元组\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1029\u002F)* - EMNLP 2019\n\n   姜天闻，赵彤，秦兵，刘挺，Nitesh Chawla，蒋梦\n   \n* *[\"“条件”的作用：一种新颖的科学知识图谱表示与构建模型\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330942)* - KDD 2019\n\n   姜天闻，赵彤，秦兵，刘挺，Nitesh V. Chawla，蒋梦\n\n* *[\"利用源文本的辅助信息对开放知识库进行规范化\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8731346)* - ICDE 2019\n\n   林雪玲，陈磊\n   \n* *[\"中文名词短语的开放关系抽取\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8903488)* - TKDE 2019\n\n   王成宇，何晓峰，周傲英\n   \n* *[\"分解与提取——拆分子句与命题抽取的解耦\"](https:\u002F\u002Facl-bg.org\u002Fproceedings\u002F2019\u002FRANLP%202019\u002Fpdf\u002FRANLP047.pdf)* - RANLP 2019\n\n   Darina Gold, Torsten Zesch\n   \n* *[\"利用开放信息抽取生成多前提蕴含语料库\"](https:\u002F\u002Facl-bg.org\u002Fproceedings\u002F2019\u002FRANLP%202019\u002Fpdf\u002FRANLP144.pdf)* - RANLP 2019\n\n   Martin Víta, Jakub Klímek\n   \n* *[\"基于词汇语法的意大利自然语言句子开放信息抽取\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417419306724)* - 专家系统与应用 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito, Giuseppe De Pietro\n   \n* *[\"弱监督、数据驱动的规则获取用于开放信息抽取\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-18305-9_2)* - CAIAC 2019\n\n   Fabrizio GottiEmail, Philippe Langlais\n\n* *[\"使用基于词嵌入的孪生网络对齐开放信息抽取关系与知识库关系\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002Fpapers\u002FW\u002FW19\u002FW19-0412\u002F)* - ICCS 2019\n\n   Rifki Afina Putri, Giwon Hong, Sung-Hyon Myaeng\n   \n* [*\"神经开放信息抽取模型中的上下文化词嵌入\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-23281-8_31) - NLDB 2019\n\n   Injy Sarhan, Marco R. Spruit\n   \n* [*\"多语言开放信息抽取：挑战与机遇\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) - 信息 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n   \n* [*\"CTGA: 基于图的生物医学文献搜索\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8983173) - IEEE 国际生物信息学与生物医学会议 (BIBM)\n\n   姜天闻，张志涵，赵彤，秦兵，刘挺，Nitesh V. Chawla，蒋梦\n   \n* [*\"当词汇语法遇见开放信息抽取：针对意大利句子的计算实验\"*](http:\u002F\u002Fceur-ws.org\u002FVol-2481\u002Fpaper36.pdf) - CLiC-it 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*\"面向意大利语开放信息抽取的黄金标准数据集构建\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*\"从开放信息抽取中协同聚类三元组\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~kpal\u002Fpaper\u002FCOMAD_2020_kpal.pdf) - COMAD 2019\n\n   Koninika Pal, Vinh Thinh Ho, Gerhard Weikum\n   \n* [*基于连贯性和显著性的多文档关系挖掘*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F332735453_Coherence_and_Salience-Based_Multi-Document_Relationship_Mining) - APWeb-WAIM 2019\n\n   Yongpan Sheng, Zenglin Xu\n\n* *[\"从阅读理解数据集中学习隐式关系的开放信息抽取\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07471)* - CoRR 2019\n\n   Jacob Beckerman, Theodore Christakis\n\n### 2020\n\n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction（开放信息抽取的神经架构与训练方法系统比较）*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n\n* [*A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression（面向开放域信息表达的自然语言谓词-函数-参数标注）*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.167\u002F) - EMNLP 2020 ([resources（资源）](https:\u002F\u002Fsunbelbd.github.io\u002FOpen-Information-eXpression\u002F))\n\n   Mingming Sun, Wenyue Hua, Zoey Liu, Xin Wang, Kangjie Zheng, Ping Li\n\n\n* [*Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction（开放信息抽取的神经架构与训练方法系统比较）*](http:\u002F\u002Fwww.cs.ox.ac.uk\u002Fpublications\u002Fpublication14256-abstract.html) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n\n\n* [*SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction（SelfORE：用于开放关系抽取的自监督关系特征学习）*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.02438.pdf) - EMNLP 2020\n\n   Xuming Hu, Chenwei Zhang, Yusong Xu, Lijie Wen, Philip S. Yu\n\n* [*\"OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction（OpenIE6：基于迭代网格标注和协调分析的开放信息抽取）\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03147) ([code（代码）](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)) - EMNLP 2020\n\n  Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti\n\n* [*\"Multi2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT（Multi2OIE：基于多头注意力机制与BERT的多语言开放信息抽取）\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.08128.pdf) ([code（代码）](https:\u002F\u002Fgithub.com\u002Fyoungbin-ro\u002FMulti2OIE)) - EMNLP 2020\n\n  Youngbin Ro, Yukyung Lee, Pilsung Kang\n  \n* [*\"On Aligning OpenIE Extractions with Knowledge Bases: A Case Study（对齐OpenIE抽取结果与知识库：案例研究）\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.eval4nlp-1.14\u002F) ([video（视频）](https:\u002F\u002Fslideslive.com\u002F38939720\u002Fon-aligning-openie-extractions-with-knowledge-bases-a-case-study), [slides（幻灯片）](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002Fpi1\u002Fopiec\u002Fdsa-ota-talk-final.pdf), [resources（资源）](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F)) - Eval4NLP@EMNLP 2020\n\n   Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke\n\n* [*\"IMoJIE: Iterative Memory-Based Joint Open Information Extraction（IMoJIE：基于迭代记忆的联合开放信息抽取）\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.521\u002F) ([code（代码）](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie), [video（视频）](https:\u002F\u002Fslideslive.com\u002F38929035\u002Fimojie-iterative-memorybased-joint-open-information-extraction)) - ACL 2020\n\n   Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti\n   \n* [*\"Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction（我们能否通过开放知识图谱嵌入预测新事实？开放链接预测基准）\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.209\u002F) ([resources（资源）](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Folpbench\u002F), [video（视频）](https:\u002F\u002Fslideslive.com\u002F38929433\u002Fcan-we-predict-new-facts-with-open-knowledge-graph-embeddings-a-benchmark-for-open-link-prediction)) - ACL 2020\n\n   Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla\n\n* [*\"Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts（通过贝叶斯结构学习在开放域事实中学习实体、关系和概念之间的可解释关系）\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.717\u002F) ([video（视频）](https:\u002F\u002Fslideslive.com\u002F38928762\u002Flearning-interpretable-relationships-between-entities-relations-and-concepts-via-bayesian-structure-learning-on-open-domain-facts)) - ACL 2020\n\n   Jingyuan Zhang, Mingming Sun, Yue Feng, Ping Li\n\n* [*\"In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts（通俗易懂：从科学文本中进行半开放关系抽取）\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.137.pdf) ([code（代码）](https:\u002F\u002Fgithub.com\u002Frubenkruiper\u002FFOBIE), [video（视频）](https:\u002F\u002Fslideslive.com\u002F38928870\u002Fin-laymans-terms-semiopen-relation-extraction-from-scientific-texts)) - ACL 2020\n\n   Ruben Kruiper, Julian Vincent, Jessica Chen-Burger, Marc Desmulliez, Ioannis Konstas\n\n* *[\"Span Model for Open Information Extraction on Accurate Corpus（基于精确语料的开放信息抽取的Span模型）\"]*(https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.10879.pdf)* ([code（代码）](https:\u002F\u002Fgithub.com\u002Fzhanjunlang\u002FSpan_OIE))- AAAI 2020\n   \n   Junlang Zhan, Hai Zhao\n   \n* *[\"LOREM: Language-consistent Open Relation Extraction from Unstructured Text（LOREM：从非结构化文本中提取语言一致的开放关系）\"]*(https:\u002F\u002Frepository.tudelft.nl\u002Fislandora\u002Fobject\u002Fuuid%3A3d9cfa08-4a7f-41cc-afdd-a8902094228c)* ([code（代码）](https:\u002F\u002Fgithub.com\u002Ftomharting\u002FLOREM)) - WWW 2020\n\n   Tom Harting, Sepideh Mesbah, Christoph Lofi\n   \n* *[\"Extracting Knowledge from Web Text with Monte Carlo Tree Search（使用蒙特卡洛树搜索从网络文本中提取知识）\"]*(https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380010)* - WWW 2020\n\n   Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li\n   \n* *[\"MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases（MULCE：基于开放知识库嵌入的多层次规范化）\"]*(https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-62005-9_23)* - WISE 2020\n\n   Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen\n\n   \n* [*An Advantage Actor-Critic Algorithm with Confidence Exploration for Open Information Extraction（一种带置信度探索的优势演员-评论家算法用于开放信息抽取）\"*](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611976236.25) - SDM 2020\n\n   Guiliang Liu, Xu Li, Miningming Sun, Ping Li\n\n   \n* *[\"Chinese Open Relation Extraction with Pointer-Generator Networks（使用指针生成网络进行中文开放关系抽取）\"]*(https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9172882\u002Freferences#references)* - DSC 2020\n\n   Ziheng Cheng, Xu Wu, Xiaqing Xie, Jingchen Wu\n   \n* *[Explainable OpenIE Classifier with Morpho-syntactic Rules（基于形态句法规则的可解释OpenIE分类器）\"](http:\u002F\u002Fceur-ws.org\u002FVol-2693\u002Fpaper1.pdf)* - HI4NLP@ECAI 2020 \n\n   Bruno Cabral, Marlo Souza, Daniela Barreiro Claro\n   \n* [*Language Models are Open Knowledge Graphs（语言模型即开放知识图谱）*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11967) - CoRR 2020\n\n   Chenguang Wang, Xiao Liu, Dawn Song\n   \n* [*\"Hybrid Neural Tagging Model for Open Relation Extraction（用于开放关系抽取的混合神经标注模型）\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.01761.pdf) - CoRR 2020 ([data（数据）](https:\u002F\u002Fgithub.com\u002FTJUNLP\u002FNSL4OIE))\n\n   Shengbin Jia, Yang Xiang\n   \n* [*\"Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network（使用多层元图神经网络规范化开放知识库）\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09610.pdf) - CoRR 2020\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n* [*\"Tag and Correct: Question Aware Open Information Extraction with Two-Stage Decoding（标记与修正：基于两阶段解码的问题感知开放信息抽取）\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.07406.pdf) - CoRR 2020\n\n   Martin Kuo, Yaobo Liang, Lei Ji, Nan Duan, Linjun Shou, Ming Gong, Peng Chen\n   \n* [*\"Abstractive Query Focused Summarization with Query-Free Resources（基于无查询资源的抽象查询聚焦摘要生成）\"*](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.14774) - CoRR 2020\n\n   Yumo Xu, Mirella Lapata\n\n### 2021\n\n* [*\"CoRI: 基于数据增强的集体关系集成用于开放信息抽取\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2106.00793.pdf) - ACL 2021\n\n   Zhengbao Jiang, Jialong Han, Bunyamin Sisman, Xin Luna Dong\n   \n* [*\"DocOIE: 一个面向开放信息抽取的文档级上下文感知数据集\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.210\u002F) - ACL 2021\n\n   Kuicai Dong, Zhao Yilin, Aixin Sun, Jung-Jae Kim, Xiaoli Li\n   \n* [*\"OKGIT: 使用隐式类型进行开放知识图谱链接预测\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.225\u002F) - ACL 2021\n\n   \tChandrahas, Partha Pratim Talukdar\n    \n* [*\"基于最大团的非自回归开放信息抽取\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.764\u002F) - EMNLP 2021\n\n    Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang\n    \n* [*\"零样本信息抽取作为统一的文本到三元组翻译\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.94\u002F) - EMNLP 2021 ([代码](https:\u002F\u002Fgithub.com\u002Fcgraywang\u002Fdeepex))\n\n    Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song\n    \n* [*\"使用变分自编码器进行开放知识图谱规范化\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.811\u002F) - EMNLP 2021 ([代码](https:\u002F\u002Fgithub.com\u002FIBM\u002FOpen-KG-canonicalization))\n\n    Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo\n   \n* [*\"LSOIE: 一个用于监督开放信息抽取的大规模数据集\"*](https:\u002F\u002Faclanthology.org\u002F2021.eacl-main.222\u002F) - EACL 2021 ([代码和数据](https:\u002F\u002Fgithub.com\u002FJacobsolawetz\u002Flarge-scale-oie)) \n\n   Jacob Solawetz, Stefan Larson\n\n* [*\"开放层次化关系抽取\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.452.pdf) - NAACL 2021 ([代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FOHRE))\n\n   Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun\n\n* [*\"半开放信息抽取\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3442381.3450029) - WWW 2021\n\n   Bowen Yu, Zhenyu Zhang, Jiawei Sheng, Tingwen Liu, Yubin Wang, Yucheng Wang, Bin Wang\n   \n* [*\"联合开放知识库规范化与链接\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3452776) - SIGMOD 2021\n\n   \tYinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan\n    \n* [*\"TENET: 基于一致性松弛的联合实体与关系链接\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n\n* [*\"多粒度依赖图神经网络用于中文开放信息抽取\"*](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n   \n* [*\"CaSIE: 开放信息抽取系统的规范化与信息选择框架\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9458825) - ICDE 2021\n\n   Hao Xin, Xueling Lin, Lei Chen\n   \n* *[PENELOPIE: 通过机器翻译实现希腊语的开放信息抽取](https:\u002F\u002Faclanthology.org\u002F2021.eacl-srw.4\u002F)* - 学生研究研讨会 @ EACL\n\n   Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis\n   \n### 2022\n\n* [*\"BenchIE: 一个多维度事实驱动的开放信息抽取评估框架\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.307\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fgkiril\u002Fbenchie))\n\n   Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n* [*\"MILIE: 模块化与迭代化的多语言开放信息抽取\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.478\u002F) - ACL 2022 \n\n   Bhushan Kotnis, Kiril Gashteovski, Daniel Rubio, Ammar Shaker, Vanesa Rodriguez-Tembras, Makoto Takamoto, Mathias Niepert, Carolin Lawrence\n\n* [*\"对齐增强的一致性翻译用于多语言开放信息抽取\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.179\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fmoie))\n\n   Keshav Kolluru, Muqeeth Mohammed, Shubham Mittal, Soumen Chakrabarti, Mausam\n\n* [*\"OIE@OIA: 一个可适应且高效的开放信息抽取框架\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.430\u002F) - ACL 2022 \n\n   Xin Wang, Minlong Peng, Mingming Sun, Ping Li\n   \n* [*\"开放关系建模：学习定义实体间的关系\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.26\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fjeffhj\u002Fopen-relation-modeling))\n\n   Jie Huang, Kevin Chang, Jinjun Xiong, Wen-mei Hwu\n   \n* [*\"DeepStruct: 面向结构预测的语言模型预训练\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.67\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fcgraywang\u002Fdeepstruct))\n\n   Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song\n      \n* [*\"AnnIE: 一个用于构建完整开放信息抽取基准的标注平台\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-demo.5\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fnfriedri\u002Fannie-annotation-platform))\n\n   Niklas Friedrich, Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n* [*\"CompactIE: 开放信息抽取中的紧凑事实表示\"*](https:\u002F\u002Faclanthology.org\u002F2022.naacl-main.65\u002F) - NAACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002FFarimaFatahi\u002FCompactIE))\n\n   Farima Fatahi Bayat, Nikita Bhutani, H. V. Jagadish\n\n* [*\"DetIE: 受目标检测启发的多语言开放信息抽取\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8073.VasilkovskyM.pdf) - AAAI 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fsberbank-ai\u002FDetIE))\n\n   Michael Vasilkovsky, Anton Alekseev, Valentin Malykh, Ilya Shenbin, Elena Tutubalina, Dmitriy Salikhov, Mikhail Stepnov, Andrey Chertok, Sergey I. Nikolenko\n\n* [*\"神经开放信息抽取综述：现状与未来方向\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.11725.pdf) - IJCAI 2022\n\n   Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Jian Sun\n   \n* [*\"2007年至2022年开放信息抽取综述\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2208.08690.pdf) - CoRR 2022\n\n   Pai Liu, Wenyang Gao, Wenjie Dong, Songfang Huang, Yue Zhang\n\n\n## 按类别分组的论文\n\n### 调研\n\n* *[\"开放信息抽取系统及其下游应用\"](https:\u002F\u002Fwww.ijcai.org\u002FProceedings\u002F16\u002FPapers\u002F604.pdf)* - IJCAI 2016\n\n  Mausam\n  \n* *[\"开放信息抽取综述\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1326)* - COLING 2018\n\n  Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh\n\n* *[\"开放信息抽取的系统化映射研究\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418303932)* -  Expert Syst. Appl. 2018\n\n  Rafael Glauber, Daniela Barreiro Claro\n  \n* [*\"多语言开放信息抽取：挑战与机遇\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) -  Information 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n   \n* [*\"神经开放信息抽取综述：现状与未来方向\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.11725.pdf) - IJCAI 2022\n\n   Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Jian Sun\n\n* [*\"2007年至2022年开放信息抽取综述\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2208.08690.pdf) - CoRR 2022\n\n   Pai Liu, Wenyang Gao, Wenjie Dong, Songfang Huang, Yue Zhang\n\n### 评估\n\n* *[\"构建大规模开放信息抽取基准\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1252)* - EMNLP 2016 ([代码](https:\u002F\u002Fgithub.com\u002FgabrielStanovsky\u002Foie-benchmark), [演讲](https:\u002F\u002Fvimeo.com\u002F239251034))\n\n  Gabriel Stanovsky, Ido Dagan\n\n* *[\"基于信息量方法的开放信息抽取评估\"](http:\u002F\u002Frali.iro.umontreal.ca\u002Frali\u002Fsites\u002Fdefault\u002Ffiles\u002Fpublis\u002FAn_informativeness_approach_to_Open_IE_evaluation%5B1%5D.pdf)* - CICLing 2016 ([幻灯片](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf), [代码+数据](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fdata\u002FCICLing_092.zip))\n\n  William Léchelle, Philippe Langlais\n\n* *[\"通过第一阶段语义角色标注评估PredPatt和开放信息抽取\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-6944)* - IWCS 2017\n\n  Sheng Zhang, Rachel Rudinger, Benjamin Van Durme\n\n* *[\"开放关系抽取系统在语义网中的评估\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0306437916304999)* - Inf. Syst. 71, 2017\n\n  Amal Zouaq, Michel Gagnon, Ludovic Jean-Louis\n  \n* *[\"RelVis: 开放信息抽取系统的基准测试\"](http:\u002F\u002Fceur-ws.org\u002FVol-1963\u002Fpaper527.pdf)* - ISWC 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n  \n* *[\"分析开放信息抽取系统的错误\"](https:\u002F\u002Faclweb.org\u002Fanthology\u002FW17-5402)* - Workshop on Building Linguistically Generalizable NLP Systems @ EMNLP 2017\n\n  Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser\n\n* *[\"科学文本上的开放信息抽取：一项评估\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FC18-1289)* - COLING 2018\n  \n  Paul T. Groth, Michael Lauruhn, Antony Scerri, Ron Daniel\n  \n* *[\"WiRe57：一个细粒度的开放信息抽取基准\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.08962.pdf)* - CoRR 2018\n\n  William Léchelle, Fabrizio Gotti, Philippe Langlais\n  \n* *[\"CaRB：一个众包的开放信息抽取基准\"](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002F\u002Fpapers\u002Femnlp19.pdf)* - EMNLP 2019 ([代码和数据](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FCaRB))\n\n   Sangnie Bhardwaj, Samarth Aggarwal and Mausam\n   \n* [*\"为意大利语开放信息抽取建立黄金标准数据集的方向\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n* [*\"对神经架构和训练方法进行系统性比较以实现开放信息抽取\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n   \n* [*\"对齐开放信息抽取结果与知识库：案例研究\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.eval4nlp-1.14\u002F) ([视频](https:\u002F\u002Fslideslive.com\u002F38939720\u002Fon-aligning-openie-extractions-with-knowledge-bases-a-case-study), [幻灯片](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002Fpi1\u002Fopiec\u002Fdsa-ota-talk-final.pdf), [资源](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F)) - Eval4NLP@EMNLP 2020\n\n   Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke\n   \n* [*\"BenchIE：一个多维度事实型开放信息抽取评估框架\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.307\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fgkiril\u002Fbenchie))\n\n   Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš\n   \n  \n### OIE 在下游应用中的使用\n\nOIE 的输出已被证明是许多下游任务的有用输入。本节列出了从 OIE 输出中受益的几个下游任务。\n\n#### 问答系统\n\n* [*\"Triple-Fact Retriever：一种可解释的多跳问答推理检索模型\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9835400) - ICDE 2022\n\n   Chengmin Wu, Enrui Hu, Ke Zhan, Lan Luo, Xinyu Zhang, Hao Jiang, Qirui Wang, Zhao Cao, Fan Yu, Lei Chen\n\n* [*\"引导生成：通过逐步重写控制难度的问答生成\"*](https:\u002F\u002Faclanthology.org\u002F2021.acl-long.465\u002F) - ACL 2021\n\n   Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng\n   \n* [*\"使用本地知识图谱构建扩展 Seq2Seq 模型到多文档输入\"*](https:\u002F\u002Faclanthology.org\u002FD19-1428.pdf) - EMNLP 2019\n\n   Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes\n\n* [*\"基于断言的问答系统与问题感知开放信息抽取\"*](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002Fdownload\u002F16705\u002F16170) AAAI 2018\n\n  Zhao Yan, Duyu Tang, Nan Duan, Shujie Liu, Wendi Wang, Daxin Jiang, Ming Zhou, Zhoujun Li\n\n* *[\"使用开放信息抽取回答复杂问题\"](http:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002FTupleInf_ACL17.pdf)* - ACL 2017\n\n  Tushar Khot, Ashish Sabharwal, Peter Clark\n\n* [*\"基于释义驱动学习的开放问答系统\"*](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP13-1158) ACL 2013 \n\n  Anthony Fader, Luke S. Zettlemoyer, Oren Etzioni\n  \n#### 槽填充（Slot Filling）\n\n* [*\"三小时内将开放信息抽取应用于 KBP 关系提取\"*](https:\u002F\u002Fpdfs.semanticscholar.org\u002Fd431\u002F81fa9af5440360d4055e1ce7ddaaa6e82d77.pdf) - TAC 2013\n\n  Stephen Soderland, John Gilmer, Robert Bart, Oren Etzioni, Daniel S. Weld\n  \n* *[\"利用语言结构进行开放域信息抽取\"](https:\u002F\u002Fnlp.stanford.edu\u002Fpubs\u002F2015angeli-openie.pdf)* - ACL 2015 ([代码 (Java)](https:\u002F\u002Fstanfordnlp.github.io\u002FCoreNLP\u002Fopenie.html), [代码 (Python)](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python))\n\n  Gabor Angeli, Melvin Jose Johnson Premkumar, Christopher D. Manning\n  \n* *[\"华盛顿大学 2015 年 KBP 冷启动槽填充系统\"](https:\u002F\u002Fwww.cs.rochester.edu\u002Fu\u002Fgkim21\u002Fpapers\u002FUWashington-KBP2015.pdf)* - TAC 2015\n\nStephen Soderland, Natalie Hawkins, Gene L. Kim, Daniel S. Weld\n   \n* *[\"结合开放信息抽取和远程监督的知识库填充（KBP）槽位填充\"](https:\u002F\u002Ftac.nist.gov\u002Fpublications\u002F2015\u002Fparticipant.papers\u002FTAC2015.UWashington.proceedings.pdf)* - TAC 2015\n\n   \tStephen Soderland, Natalie Hawkins, John Gilmer, Daniel S. Weld\n   \n* *[\"开放关系抽取与落地\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FI17-1086\u002F)* - IJCNLP 2017\n\n   Dian Yu, Lifu Huang, Heng Ji\n\n\n#### 事件抽取 (Event Extraction)\n\n* [*\"大规模生成连贯的事件模式\"*](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Femnlp-2013-niranjan.pdf) - EMNLP 2013\n\n  Niranjan Balasubramanian, Stephen Soderland, Mausam, Oren Etzioni\n\n* [*\"通过密集标注实现跨文档事件身份识别\"*](https:\u002F\u002Faclanthology.org\u002F2021.conll-1.39\u002F) - CoNLL 2021\n\n   Adithya Pratapa, Zhengzhong Liu, Kimihiro Hasegawa, Linwei Li, Yukari Yamakawa, Shikun Zhang, Teruko Mitamura\n\n#### 文本摘要 (Text Summarization)\n\n* [*\"重要的事实\"*](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD18-1129) - EMNLP 2018\n\n  Marco Ponza, Luciano Del Corro, Gerhard Weikum\n  \n* [*\"使用局部知识图构建扩展序列到序列模型以处理多文档输入\"*](https:\u002F\u002Faclanthology.org\u002FD19-1428.pdf) - EMNLP 2019\n\n   Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes\n  \n* [*\"基于连贯性和显著性的多文档关系挖掘\"*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F332735453_Coherence_and_Salience-Based_Multi-Document_Relationship_Mining) - APWeb-WAIM 2019\n\n   Yongpan Sheng, Zenglin Xu\n   \n* [*\"FAR-ASS：基于事实感知的强化抽象句子摘要生成\"*](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0306457320309675) - 信息处理与管理 2021\n\n   Mengli Zhanga, Gang Zhoua, Wanting Yua, Wenfen Liu\n   \n* [*\"Summary Explorer：可视化文本摘要领域的最新进展\"*](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-demo.22\u002F) - EMNLP 2021\n\n   Shahbaz Syed, Tariq Yousef, Khalid Al Khatib, Stefan Jänicke, Martin Potthast\n\n   \n* [*\"从无查询资源生成面向查询的摘要\"*](https:\u002F\u002Faclanthology.org\u002F2021.acl-long.475\u002F) - ACL 2021\n\n   Yumo Xu, Mirella Lapata\n   \n* [*\"高效总结多文档集群的文本和图编码\"*](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.380.pdf) - NAACL 2021\n\n   Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, Markus Dreyer\n   \n* [*\"通过话语和动作图进行结构感知的抽象对话摘要生成\"*](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.109\u002F) - NAACL 2021\n\n   Jiaao Chen, Diyi Yang\n\n   \n* [*\"聚焦于行动：联合学习高亮和摘要以生成电子邮件待办事项摘要\"*](https:\u002F\u002Faclanthology.org\u002F2022.findings-acl.323\u002F) - ACL 2022\n\n   Kexun Zhang, Jiaao Chen, Diyi Yang\n   \n* [*\"FactGraph：使用语义图表示评估摘要中的事实性\"*](https:\u002F\u002Faclanthology.org\u002F2022.naacl-main.236\u002F) - NAACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Famazon-research\u002Ffact-graph))\n\n   Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal\n\n#### 知识库填充 (Knowledge Base Population)\n\n* [*\"Pocket Knowledge Base Population\"*](https:\u002F\u002Fwww.cs.jhu.edu\u002F~mdredze\u002Fpublications\u002F2017_acl_pocket_kb.pdf) - ACL 2017\n\n  Travis Wolfe, Mark Dredze, Benjamin Van Durme\n  \n* [*\"KBPearl：由实体和关系联合链接支持的知识库填充系统\"*](http:\u002F\u002Fwww.vldb.org\u002Fpvldb\u002Fvol13\u002Fp1035-lin.pdf) - PVLDB 2020\n\n  Xueling Lin, Haoyang Li, Hao Xin, Zijian Li, Lei Chen\n  \n#### 知识库构建 (Knowledge Base Construction)\n\n* *[\"“条件”的作用：一种新颖的科学知识图表示与构建模型\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3292500.3330942)* - KDD 2019\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n#### 实体链接 (Entity Linking)\n\n* [*\"TENET：通过一致性松弛进行实体和关系的联合链接\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n    \n#### 关系链接 (Relation Linking)\n\n* [*\"TENET：通过一致性松弛进行实体和关系的联合链接\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3457280) - SIGMOD 2021\n\n    Xueling Lin, Lei Chen, Chaorui Zhang\n    \n* [*\"捕获语义类型的关系模式中的知识以增强关系链接\"*](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3148011.3148031) - K-CAP 2017\n\n    Kuldeep Singh, Isaiah Onando Mulang', Ioanna Lytra, Mohamad Yaser Jaradeh, Ahmad Sakor, Maria-Esther Vidal, Christoph Lange, Sören Auer\n   \n#### 开放链接预测 (Open Link Prediction)\n\n* [*\"OKGIT：使用隐式类型的开放知识图链接预测\"*](https:\u002F\u002Faclanthology.org\u002F2021.findings-acl.225\u002F) - ACL 2021\n\n   \tChandrahas, Partha Pratim Talukdar\n    \n* [*\"我们能否用开放知识图嵌入预测新事实？开放链接预测的基准测试\"*](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.209\u002F) ([资源](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Folpbench\u002F), [视频](https:\u002F\u002Fslideslive.com\u002F38929433\u002Fcan-we-predict-new-facts-with-open-knowledge-graph-embeddings-a-benchmark-for-open-link-prediction)) - ACL 2020\n\n   Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla\n   \n#### 关系抽取 (Relation Extraction)\n\n* [*\"RESIDE：利用辅助信息改进远距离监督神经关系抽取\"*](https:\u002F\u002Faclanthology.org\u002FD18-1157.pdf) - EMNLP 2018\n\n   Shikhar Vashishth, Rishabh Joshi, Sai Suman Prayaga, Chiranjib Bhattacharyya, Partha Talukdar\n\n#### 实体关联 (Relating Entities)\n\n* [*\"通过开放信息抽取关联法律实体\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-14401-2_17) - MTSR 2018\n  \n  Giovanni Siragusa, Rohan Nanda, Valeria De Paiva, Luigi Di Caro\n  \n#### 故事理解 (Story Comprehension)\n\n* [*\"通过动态文档知识图增强大型语言模型的故事理解能力\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-10221.AndrusB.pdf) - AAAI 2022\n\n   Berkeley Andrus, Yeganeh Nasiri, Jay Cui, Ben Cullen, Nancy Fulda\n\n#### 文本生成 (Text Generation)\n\n* [*\"一个无监督的联合系统，用于从知识图生成文本和语义解析\"*](https:\u002F\u002Faclanthology.org\u002F2020.emnlp-main.577.pdf) - EMNLP 2020\n\n   Martin Schmitt, Sahand Sharifzadeh, Volker Tresp, Hinrich Schütze\n\n#### 视频定位 (Video Grounding)\n\n* *[\"使用双重对比学习的干预性视频定位\"](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FNan_Interventional_Video_Grounding_With_Dual_Contrastive_Learning_CVPR_2021_paper.pdf)* - CVPR 2021\n\n  Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu\n  \n\n\n### 不同语言中的开放信息抽取 (OIE in Different Languages)\n\n大多数开放信息抽取（OIE）系统专注于从英文文本中提取信息。然而，一些OIE系统要么专注于非英语语言，要么是多语言的。在本节中，列出了非英语语言或多语言的OIE系统。\n\n#### 多语言OIE系统\n\n* [*\"MILIE: 模块化与迭代式多语言开放信息抽取\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.478\u002F) - ACL 2022 \n\n   Bhushan Kotnis, Kiril Gashteovski, Daniel Rubio, Ammar Shaker, Vanesa Rodriguez-Tembras, Makoto Takamoto, Mathias Niepert, Carolin Lawrence\n   \n* [*\"基于对齐增强的一致性翻译的多语言开放信息抽取\"*](https:\u002F\u002Faclanthology.org\u002F2022.acl-long.179\u002F) - ACL 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fmoie))\n\n   Keshav Kolluru, Muqeeth Mohammed, Shubham Mittal, Soumen Chakrabarti, Mausam\n\n* [*\"DetIE: 受目标检测启发的多语言开放信息抽取\"*](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8073.VasilkovskyM.pdf) - AAAI 2022 ([代码](https:\u002F\u002Fgithub.com\u002Fsberbank-ai\u002FDetIE)\n\n   Michael Vasilkovsky, Anton Alekseev, Valentin Malykh, Ilya Shenbin, Elena Tutubalina, Dmitriy Salikhov, Mikhail Stepnov, Andrey Chertok, Sergey I. Nikolenko\n\n\n* [*\"Multi2OIE: 基于多头注意力机制和BERT的多语言开放信息抽取\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.08128.pdf) ([代码](https:\u002F\u002Fgithub.com\u002Fyoungbin-ro\u002FMulti2OIE)) - EMNLP 2020\n\n  Youngbin Ro, Yukyung Lee, Pilsung Kang\n\n* *[\"LOREM: 从非结构化文本中提取语言一致的开放关系\"](https:\u002F\u002Frepository.tudelft.nl\u002Fislandora\u002Fobject\u002Fuuid%3A3d9cfa08-4a7f-41cc-afdd-a8902094228c)* ([代码](https:\u002F\u002Fgithub.com\u002Ftomharting\u002FLOREM)) - WWW 2020\n\n   Tom Harting, Sepideh Mesbah, Christoph Lofi\n   \n* *[基于形态句法规则的可解释开放信息抽取分类器\"](http:\u002F\u002Fceur-ws.org\u002FVol-2693\u002Fpaper1.pdf)* - HI4NLP@ECAI 2020 \n\n   Bruno Cabral, Marlo Souza, Daniela Barreiro Claro\n\n* [*\"多语言开放信息抽取：挑战与机遇\"*](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201905.0029\u002Fdownload\u002Ffinal_file) -  Information 10(7): 228, 2019\n\n   Daniela Barreiro Claro, Marlo Souza, Clarissa Castellã Xavier, Leandro Souza de Oliveira\n\n* [*\"使用跨语言投影的多语言开放关系抽取\"*](https:\u002F\u002Fstatic.googleusercontent.com\u002Fmedia\u002Fresearch.google.com\u002Fen\u002F\u002Fpubs\u002Farchive\u002F43449.pdf) - HLT-NAACL 2015\n\n  Manaal Faruqui, Shankar Kumar\n  \n* *[\"MT\u002FIE: 使用神经序列到序列模型的跨语言开放信息抽取\"](http:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FE17-2011)* - EACL 2017 ([代码](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie))\n  \t\n  Kevin Duh, Benjamin Van Durme, Sheng Zhang\n\n* [*\"多语言开放信息抽取\"*](https:\u002F\u002Fgramatica.usc.es\u002F~gamallo\u002Fartigos-web\u002FEPIA2015.pdf) - EPIA 2015\n\n  Pablo Gamallo, Marcos García\n\n#### 德语语言的 OIE 系统\n\n* [*\"GerIE - 一个面向德语的开放信息抽取系统\"*](http:\u002F\u002Fwww.jucs.org\u002Fjucs_24_1\u002Fgerie_an_open_information\u002Fjucs_24_01_0002_0024_bassa.pdf) - J. UCS 2018\n\n  Akim Bassa, Mark Kröll, Roman Kern\n  \n* [*\"将开放信息抽取系统从英语移植到德语\"*](https:\u002F\u002Faclweb.org\u002Fanthology\u002FD16-1086) - EMNLP 2016 ([代码](https:\u002F\u002Fgithub.com\u002FUKPLab\u002Fprops-de))\n\n  Tobias Falke, Gabriel Stanovsky, Iryna Gurevych, Ido Dagan\n\n#### 葡萄牙语语言的 OIE 系统\n\n* [*\"葡萄牙语开放信息抽取注释任务的挑战\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-99722-3_7) - PROPOR 2018\n\n  Rafael Glauber, Leandro Souza de Oliveira, Cleiton Fernando Lima Sena, Daniela Barreiro Claro, Marlo Souza\n\n* [*\"通过推理方法增强葡萄牙语开放信息抽取\"*](http:\u002F\u002Fwww.scitepress.org\u002FPapers\u002F2017\u002F63382\u002F63382.pdf) - ICEIS 2017\n  \n  Cleiton Fernando Lima Sena, Rafael Glauber, Daniela Barreiro Claro\n  \n* [*\"DependentIE: 基于依存分析的葡萄牙语开放信息抽取系统\"*](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FRafael_Glauber\u002Fpublication\u002F324759625_DependentIE_An_Open_Information_Extraction_system_on_Portuguese_by_a_Dependence_Analysis\u002Flinks\u002F5ae0e48faca272fdaf8d8979\u002FDependentIE-An-Open-Information-Extraction-system-on-Portuguese-by-a-Dependence-Analysis.pdf) - ENIAC 2017\n\n  Leandro Souza de Oliveira, Rafael Glauber, Daniela Barreiro Claro\n  \n#### 西班牙语语言的 OIE 系统\n\n* *[\"基于句法约束的西班牙语开放信息抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP14-3011.pdf)* - ACL（学生研究研讨会）(2014)\n\n  Alisa Zhila, Alexander Gelbukh\n  \n#### 中文语言的 OIE 系统\n\n* *[\"ZORE: 一个基于句法的中文开放关系抽取系统\"](http:\u002F\u002Faclweb.org\u002Fanthology\u002FD14-1201)* - EMNLP 2014\n\n  Likun Qiu, Yue Zhang\n  \n* *[\"中文开放关系抽取与知识库构建\"](https:\u002F\u002Fai2-website.s3.amazonaws.com\u002Fpublications\u002F10094_Paper.pdf)* - ACM Trans. Asian & Low-Resource Lang. Inf. Process. 2018 ([幻灯片](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf), [代码](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction))\n\n  Shengbin Jia, Shijia E, Maozhen Li, Yang Xiang\n  \n* *[\"中文名词短语的开放关系抽取\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8903488)* - TKDE 2019\n\n   Chengyu Wang, Xiaofeng He, Aoying Zhou\n   \n* *[\"基于指针生成网络的中文开放关系抽取\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9172882\u002Freferences#references)* - DSC 2020\n\n   Ziheng Cheng, Xu Wu, Xiaqing Xie, Jingchen Wu\n   \n* [*\"基于多粒度依赖图神经网络的中文开放信息抽取\"*](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n  \n#### 波斯语语言的 OIE 系统\n\n* [*\"RePersian: 一个高效的波斯语开放信息抽取工具\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9122301\u002Fauthors#authors) - ICWR 2020\n\n  Raana Saheb-Nassagh, Majid Asgari, Behrouz Minaei-Bidgoli\n\n* [*\"一种用于波斯语文本开放信息抽取的递归算法\"*](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F325977333_A_recursive_algorithm_for_open_information_extraction_from_Persian_texts) - IJCAT 2018\n\n  Mahmoud Rahat, Alireza Talebpour, Seyedamin Monemian\n  \n* [*\"作为波斯语文本摘要中间语义结构的开放信息抽取\"*](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs00799-018-0244-z) - 国际数字图书馆期刊 (2018)\n\n  Mahmoud Rahat, Alireza Talebpour\n  \n* [*\"Parsa: 一个波斯语开放信息抽取系统\"*](https:\u002F\u002Facademic.oup.com\u002Fdsh\u002Farticle\u002F33\u002F4\u002F874\u002F4951677) - DSH 2018\n\n  Mahmoud Rahat, Alireza Talebpour\n  \n#### 意大利语语言的 OIE 系统\n\n* *[\"基于词汇语法的意大利语自然句子开放信息抽取\"](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417419306724)* - 专家系统与应用 2019\n\nRaffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito, Giuseppe De Pietro\n   \n* [*\"Towards a gold standard dataset for Open Information Extraction in Italian\"*](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8931822) - SNAMS 2019\n\n   Raffaele Guarasci, Emanuele Damiano, Aniello Minutolo, Massimo Esposito\n   \n#### 面向印尼语的 OIE 系统（OIE Systems for Indonesian Language）\n\n* *[基于规则的印尼语开放信息抽取](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8541293)* - ICAICTA 2018 \n\n  Ade Romadhony, Ayu Purwarianti, Dwi H. Widyantoro\n  \n#### 面向希腊语的 OIE 系统（OIE Systems for Greek Language）\n\n* *[PENELOPIE: 通过机器翻译实现希腊语的开放信息抽取](https:\u002F\u002Faclanthology.org\u002F2021.eacl-srw.4\u002F)* - 学生研究研讨会 @ EACL\n\n   Dimitris Papadopoulos, Nikolaos Papadakis, Nikolaos Matsatsinis\n\n\n\n### 监督式 OIE（Supervised OIE）\n\n* [*\"监督式开放信息抽取\"*](https:\u002F\u002Faclweb.org\u002Fanthology\u002FN18-1081) - NAACL-HLT 2018\n\n  Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan\n\n* [*\"神经网络开放信息抽取\"*](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.04270.pdf) - ACL 2018\n\n  Lei Cui, Furu Wei, Ming Zhou\n  \n* *[\"Logician: 一种统一的端到端神经方法用于开放域信息抽取\"](https:\u002F\u002Ftianjun.me\u002Fstatic\u002Fessay_resources\u002FRelationExtraction\u002FPaper\u002F2018_Logician_A_Unified_End-to-End_Neural_Approach_for_open_domain_IE(1).pdf)* - WSDM 2018\n\n  Mingming Sun, Xu Li, Xin Wang, Miao Fan, Yue Feng, Ping Li\n  \n* [*\"Logician 和 Orator: 在开放域中从语言与知识的二元性学习\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD18-1236) - EMNLP 2018\n\n   Mingming Sun, Xu Li, Ping Li\n   \n* *[\"监督无监督的开放信息抽取模型\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FD19-1067.pdf)* - EMNLP 2019\n\n   Arpita Roy, Youngja Park, Taesung Lee and Shimei Pan\n   \n* [*\"在神经开放信息抽取模型中的上下文化词嵌入\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-23281-8_31) - NLDB 2019\n\n   Injy Sarhan, Marco R. Spruit\n\n* [*\"弱监督、数据驱动的开放信息抽取规则获取\"*](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-18305-9_2) - CAIAC 2019\n\n   Fabrizio GottiEmail, Philippe Langlais\n   \n* [*\"从阅读理解数据集中学习隐含关系的开放信息抽取\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07471) - CoRR 2019\n\n   Jacob Beckerman, Theodore Christakis\n   \n* *[\"精确语料库上的开放信息抽取的跨度模型\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.10879.pdf)* ([代码](https:\u002F\u002Fgithub.com\u002Fzhanjunlang\u002FSpan_OIE))- AAAI 2020\n   \n   Junlang Zhan, Hai Zhao\n   \n* *[\"使用蒙特卡洛树搜索从网页文本中提取知识\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380010)* - WWW 2020\n\n   Guiliang Liu, Xu Li, Jiakang Wang, Mingming Sun, Ping Li\n   \n* [*\"一种具有置信探索的优势演员-评论家算法用于开放信息抽取\"](https:\u002F\u002Fepubs.siam.org\u002Fdoi\u002Fabs\u002F10.1137\u002F1.9781611976236.25) - SDM 2020\n\n   Guiliang Liu, Xu Li, Miningming Sun, Ping Li\n   \n* [*\"面向开放关系抽取的混合神经标注模型\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.01761.pdf) - CoRR 2020 ([数据](https:\u002F\u002Fgithub.com\u002FTJUNLP\u002FNSL4OIE))\n\n   Shengbin Jia, Yang Xiang   \n   \n* [*\"IMoJIE: 基于迭代记忆的联合开放信息抽取\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.521\u002F) ([代码](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie)) - ACL 2020\n\n   Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti\n   \n* [*\"OpenIE6: 迭代网格标注和协调分析用于开放信息抽取\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.03147) ([代码](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)) - EMNLP 2020\n\n  Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti\n   \n* [*\"开放信息抽取的神经架构和训练方法的系统比较\"](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.690) - EMNLP 2020\n\n   Patrick Hohenecker, Frank Mtumbuka, Vid Kocijan, Thomas Lukasiewicz\n   \n* [*\"多粒度依赖图神经网络用于中文开放信息抽取\"](https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002F978-3-030-75768-7_13.pdf) - PAKDD 2021\n\n   Zhiheng Lyu, Kaijie Shi, Xin Li, Lei Hou, Juanzi Li, Binheng Song\n\n### OIE 的规范化（Canonicalization of OIE）\n\n* *[\"规范化开放知识库\"](https:\u002F\u002Fsuchanek.name\u002Fwork\u002Fpublications\u002Fcikm2014.pdf)* - CIKM 2014\n\n  Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek\n  \n* *[\"CESI: 使用嵌入和辅助信息进行开放知识库规范化\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3186030)* - WWW 2018 ([代码](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi))\n  \n  Shikhar Vashishth, Prince Jain, Partha Talukdar\n  \n* *[\"迈向实用的开放知识库规范化\"](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3271707)* - CIKM 2018\n\n   Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, Pengcheng Yin\n  \n* *[\"CaRe: 开放知识图谱嵌入\"](http:\u002F\u002Ftalukdar.net\u002Fpapers\u002FCaRe_EMNLP2019.pdf)* - EMNLP 2019 ([代码](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FCaRE))\n\n   Swapnil Gupta, Sreyash Kenkre, Partha Talukdar\n   \n* *[\"使用源文本辅助信息进行开放知识库规范化\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8731346)* - ICDE 2019\n\n   Xueling Lin, Lei Chen\n   \n* *[\"MULCE: 使用开放知识库嵌入的多层次规范化\"](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-62005-9_23)* - WISE 2020\n\n   Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen\n   \n* [*\"使用多层元图神经网络进行开放知识库规范化\"](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09610.pdf) - CoRR 2020\n\n   Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang\n   \n* [*\"使用变分自编码器进行开放知识图谱规范化\"](https:\u002F\u002Faclanthology.org\u002F2021.emnlp-main.811\u002F) - EMNLP 2021 ([代码](https:\u002F\u002Fgithub.com\u002FIBM\u002FOpen-KG-canonicalization))\n\n    Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo\n   \n* [*\"联合开放知识库规范化与链接\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3448016.3452776) - SIGMOD 2021\n\n   \tYinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan\n    \n* [*\"CaSIE: 规范化并选择性地提取 OpenIE 系统的信息\"](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9458825) - ICDE 2021\n\n   Hao Xin, Xueling Lin, Lei Chen\n   \n* [*\"多视图聚类用于开放知识库规范化\"](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3534678.3539449) - KDD 2022\n\n   Wei Shen, Yang Yang, Yinan Liu\n\n## 幻灯片\n* [\\[pdf\\] *\"Compact Open Information Extraction on Large Corpora\"*](https:\u002F\u002Fwww.uni-mannheim.de\u002Fmedia\u002FEinrichtungen\u002Fdws\u002FFiles_People\u002FResearchers\u002Fgashteovski\u002Foie_nec_labs_gashteovski.pdf)。Kiril Gashteovski 于 2019 年在 NEC 欧洲实验室有限公司的演讲。\n* [\\[pdf\\] *\"(信息抽取) 第十讲 – 本体与开放信息抽取 (Ontological and Open IE)\"*](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002Finformation_extraction_2015_lecture\u002F10_ontological_and_open_IE.pdf)：关于开放信息抽取（Open IE）的讲座，是[\"信息抽取\"](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002Finformation_extraction_2018_lecture\u002F)课程的一部分，由[Prof. Dr. Alexander Fraser](http:\u002F\u002Fwww.cis.uni-muenchen.de\u002F~fraser\u002F)（慕尼黑大学 LMU）提供。\n* 开放信息抽取教程：[面向问答的开放信息抽取](https:\u002F\u002Fwww.slideshare.net\u002Fandrenfreitas\u002Fopen-ie-tutorial-2018)，作者为[André Freitas](http:\u002F\u002Fandrefreitas.org\u002F)。该教程在 OKBQA 2018 上展示。\n* [\\[pdf\\] \"中文开放关系抽取与知识库构建\"](https:\u002F\u002Fhong.xmu.edu.cn\u002F__local\u002FB\u002F68\u002FC0\u002F92B8F8DC6AC06A3F256E1FE1A6F_9556CC90_4CCA5D.pdf?e=.pdf)，2018 年。\n* [\\[pdf\\] *\"开放信息抽取（Open-IE）系统简介与综述\"*](https:\u002F\u002Fece.umd.edu\u002F~smiran\u002FOpenIE.pdf)。Sina Miran 的项目展示。\n* [\\[pdf\\] *\"开放信息抽取系统及其下游应用\"*](https:\u002F\u002Fhomes.cs.washington.edu\u002F~mausam\u002Fpapers\u002Fijcai16-earlycareer.pdf)，作者为[Prof. Mausam](http:\u002F\u002Fwww.cse.iitd.ernet.in\u002F~mausam\u002F)。该演讲在[IJCAI 2016](http:\u002F\u002Fijcai-16.org\u002F)上发表。\n* [\\[pptx\\] *\"从网络中进行开放信息抽取\"*](https:\u002F\u002Fakbcwekex2012.files.wordpress.com\u002F2012\u002F06\u002Fslides-oren.pptx)，由[Prof. Oren Etzioni](https:\u002F\u002Fallenai.org\u002Fteam\u002Forene\u002F)展示。该教程在[AKBC-WEKEX 2012](https:\u002F\u002Fakbcwekex2012.wordpress.com\u002F)上发表。\n* [\\[pdf\\] *\"ClausIE: 基于子句的开放信息抽取\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro13clausie-slides.pdf)，作者为[Luciano del Corro](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002F)。\n* [\\[pdf\\] *\"开放信息抽取：第二代\"*](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fcourses\u002Fcol864\u002Fspring2017\u002Fslides\u002F03-openie.pdf)。\n* [\\[pdf\\] *\"开放信息抽取：我们走向何方？\"*](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002Ftalks\u002Ftalk_OIE.pdf)，作者为[Claudio Delli Bovi](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002F)，2016 年。\n* [\\[pdf\\] *\"基于信息量方法的开放信息抽取评估\"*](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002Fpapers\u002F2016-CICLING.pdf)，作者为[William Léchelle](http:\u002F\u002Fwww-etud.iro.umontreal.ca\u002F~lechellw\u002F)，2016 年。\n\n## 演讲\n\n* [*\\[视频\\] \"从网络中进行开放信息抽取\"*](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=lMiLiPjGays&feature=youtu.be)，作者为[Prof. Oren Etzioni](https:\u002F\u002Fallenai.org\u002Fteam\u002Forene\u002F)，在[AKBC-WEKEX 2012](https:\u002F\u002Fakbcwekex2012.wordpress.com\u002F)上展示。\n幻灯片：[\\[pptx\\]](https:\u002F\u002Fakbcwekex2012.files.wordpress.com\u002F2012\u002F06\u002Fslides-oren.pptx)\n* [*\\[视频\\] \"开放信息抽取：我们走向何方？\"*](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=EhOF_AbDwcE)，作者为[Claudio Delli Bovi](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002F)。该演讲于 2016 年在 AI2 发表。[幻灯片 \\[pdf\\]](http:\u002F\u002Fwwwusers.di.uniroma1.it\u002F~dellibovi\u002Ftalks\u002Ftalk_OIE.pdf)\n* [*\\[视频\\] \"开放信息抽取中的嵌套命题\"*](https:\u002F\u002Fvimeo.com\u002F239245885)，Nikita Bhutani 在 EMNLP 2016 上发表。\n* [*\\[视频\\] \"创建一个大型开放信息抽取基准测试\"*](https:\u002F\u002Fvimeo.com\u002F239251034)，Gabriel Stanovsky 在 EMNLP 2016 上发表。\n* [*\\[视频\\] \"OpenCeres：当开放信息抽取遇到半结构化网络\"*](https:\u002F\u002Fvimeo.com\u002F355837778)，Colin Lockard 在 NAACL 2019 上发表。[幻灯片 \\[pdf\\]](https:\u002F\u002Fhomes.cs.washington.edu\u002F~lockardc\u002FOpenCeres_NAACL_talk.pdf)\n\n## 代码\n\n* MinIE: 开放信息抽取系统 (Open Information Extraction System)\n  * [MinIE](https:\u002F\u002Fgithub.com\u002Fuma-pi1\u002Fminie): 最初用 Java 编写\n  * [MinIE 的 Python 封装](https:\u002F\u002Fgithub.com\u002Fmmxgn\u002Fminiepy)\n  * [MinScIE](https:\u002F\u002Fgithub.com\u002Fgkiril\u002FMinSCIE) - 一种开放信息抽取系统，提供结构化知识并附带引用的语义信息（基于 MinIE）。\n  * [SalIE](https:\u002F\u002Fgithub.com\u002Fmponza\u002FSalIE) - 显著性开放信息抽取系统（基于 MinIE）\n* ClausIE: 基于子句的 OIE (Clause-based OIE)\n  * [ClausIE](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fsoftware\u002Fclausie\u002F): 最初用 Java 编写\n  * [ClausIE（Maven 化版本）](https:\u002F\u002Fgithub.com\u002FIsaacChanghau\u002FClausIE)\n  * [ClausIEpy](https:\u002F\u002Fgithub.com\u002Fdrwiner\u002FClausIEpy): ClausIE 的 Python 封装\n* IIT Delhi 的 OpenIE:\n  * [OpenIE6](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fopenie6)\n  * [IMoJIE](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fimojie): 一种基于 BERT 的开放信息抽取系统\n  * [OpenIE5](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002FOpenIE-standalone)\n* UW 的 OpenIE:\n  * [OLLIE](http:\u002F\u002Fknowitall.github.io\u002Follie\u002F)\n  * [ReVerb](http:\u002F\u002Freverb.cs.washington.edu\u002F)\n* 斯坦福大学的 OpenIE:\n  * [Stanford OpenIE](https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002Fopenie.html): 斯坦福大学的开放信息抽取系统。\n  * [Stanford OpenIE Spider](https:\u002F\u002Fgithub.com\u002Fliaoziyang\u002FOpenIE-Spider): 使用斯坦福开放信息抽取从网络语料库中提取信息。\n  * [Stanford OpenIE 的 Python 封装](https:\u002F\u002Fgithub.com\u002Fphilipperemy\u002FStanford-OpenIE-Python): 非官方跨平台的 Python 封装，用于斯坦福大学提供的先进信息抽取库。\n* [Graphene:](https:\u002F\u002Fgithub.com\u002FLambda-3\u002FGraphene) 包含指代消解、简化和开放关系抽取流水线的开放信息抽取系统\n* [EXEMPLAR](https:\u002F\u002Fgithub.com\u002FU-Alberta\u002Fexemplar)\n* [DefIE:](https:\u002F\u002Fgithub.com\u002Fclaudio-db\u002FdefIE) 从文本定义中进行开放信息抽取\n* [ReMine:](https:\u002F\u002Fgithub.com\u002FGentleZhu\u002FReMine) 整合局部与全局一致性以实现开放信息抽取\n* 针对非英语语言或跨语言系统的 OIE 系统：\n   * [Zhopenie - 中文 OIE](https:\u002F\u002Fgithub.com\u002Ftim5go\u002Fzhopenie): 用 Python 编写的中文开放信息抽取系统。\n   * [中文开放关系抽取](https:\u002F\u002Fgithub.com\u002Flemonhu\u002Fopen-entity-relation-extraction): 基于依存句法的开放领域文本知识三元组抽取（实体与关系抽取）及知识库构建（针对**中文**）。\n   * [Baaz](https:\u002F\u002Fgithub.com\u002Fsobhe\u002Fopenie): 从波斯语网页中进行开放信息抽取（Python）。\n   * [MT\u002FIE](https:\u002F\u002Fgithub.com\u002Fsheng-z\u002Fcross-lingual-open-ie): 跨语言开放信息抽取。基于注意力机制的序列到序列模型，用于跨语言开放信息抽取。使用 Python 编写。\n   * [德语网站的关系抽取](https:\u002F\u002Fgithub.com\u002Ftabergma\u002Frelation-extraction): 该存储库包含三种针对德语的开放信息抽取方法。\n   * [DptOIE:](https:\u002F\u002Fgithub.com\u002FFORMAS\u002FDptOIE) 基于依存分析的葡萄牙语开放信息抽取系统。\n   * [PragmaticOIE:](https:\u002F\u002Fgithub.com\u002FFORMAS\u002FPragmaticOIE) 一种基于规则的方法，用于在第一实用层面提取葡萄牙语中的事实。\n* [CORE:](https:\u002F\u002Fgithub.com\u002Ffabiopetroni\u002FCORE) 基于因子分解机的上下文感知开放关系抽取\n* [CESI:](https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002Fcesi) 使用嵌入和辅助信息规范化开放知识库\n* [IMPLIE:](https:\u002F\u002Fgithub.com\u002Fknowitall\u002Fimplie) IMPLIE（隐式关系信息抽取）是一种程序，可从英文句子中提取二元关系，其中两个实体之间的关系并未在文本中明确表达。\n* [Ranking:](https:\u002F\u002Fgithub.com\u002Fjzbjyb\u002Foie_rank) 迭代排名感知开放信息抽取（置信度评分）。\n\n\n## 数据\n\nOIE 输出作为许多其他下游任务（如问答、事件模式归纳或生成推理规则）的有用输入。此外，OIE 输出可以用作“燃料”来衍生更多资源。这里的数据分为两大类：1) OIE 语料库；2) 从 OIE 输出衍生的资源。\n\n### OIE 语料库\n\n* [OPIEC: 一个开放信息抽取语料库:](https:\u002F\u002Fwww.uni-mannheim.de\u002Fdws\u002Fresearch\u002Fresources\u002Fopiec\u002F) 至今最大的 OIE 语料库，包含从整个英文维基百科中提取的超过 3.41 亿个三元组。语料库中的每个三元组都由丰富的元数据组成：subj \u002F obj \u002F rel 中的每个标记以及 NLP 注释（词性标注、命名实体识别标签等）、来源句子及其依存句法解析、原始（黄金标准）维基百科内容、句子顺序、时空信息等。\n* [\\[.gz\\] ReVerb 抽取结果](http:\u002F\u002Freverb.cs.washington.edu\u002Freverb_clueweb_tuples-1.1.txt.gz): 来自 OIE 系统 ReVerb 的 1500 万高精度 OIE 抽取结果（压缩后 826MB）。这些抽取结果来自 [ClueWeb09 语料库](https:\u002F\u002Flemurproject.org\u002Fclueweb09\u002F)。数据包含 *(主语, 关系, 宾语)* 三元组，并附带置信度评分（估计三元组正确抽取的可能性）和出处信息（抽取三元组的网页链接）。\n* [ReVerb 抽取结果（带链接）](http:\u002F\u002Fknowitall.cs.washington.edu\u002Flinked_extractions\u002F): 300 万个带有链接参数的三元组（1500 万高精度 ReVerb 抽取结果的一个子集）。链接（到 Freebase）由实体链接器提供。数据字段包括：*参数 1, 关系短语, 参数 2, 参数 1 链接的 Freebase ID, 对应的 Freebase 实体名称, 链接得分, 链接歧义得分*\n* [PATTY](https:\u002F\u002Fwww.mpi-inf.mpg.de\u002Fdepartments\u002Fdatabases-and-information-systems\u002Fresearch\u002Fyago-naga\u002Fpatty\u002F): PATTY 是一个系统，它获取两个参数之间的开放关系，将它们结构化为关系同义集，然后将其组织成一个分类体系。该资源包含超过 1500 万个三元组，其参数已消歧（链接到维基百科文章），并在它们之间具有关系同义集 ID。此外，该资源还包含：1) 带类型签名的关系模式同义集；2) 关系模式包含关系；3) 关系同义表达；4) 评估数据；\n* [WiseNet（1.0 和 2.0）](http:\u002F\u002Flcl.uniroma1.it\u002Fwisenet\u002F): 与 PATTY 类似，WiseNet 1.0\u002F2.0 是一个包含 OIE 三元组的资源，其中参数已消歧，开放关系被组织成关系同义集并进行分类。PATTY 和 WiseNet 的主要区别之一是 WiseNet 包含参数的“黄金链接”（由人工注释），同时保留了来自维基百科文章的原始链接。\n* [KB-Unify](http:\u002F\u002Flcl.uniroma1.it\u002Fkb-unify\u002F): KB-Unify 接收多个 OIE 语料库作为输入，并将它们统一到一个单一的消歧 OIE 存储库中。开放关系被组织成关系同义集，参数通过 BabelFy 进行消歧。\n\n### Resources derived from OIE output\n\n* [Functional relations](http:\u002F\u002Fknowitall.cs.washington.edu\u002Fleibniz\u002F): 10K Functional relations. This resource comes from the paper [*\"Identifying Functional Relations in Web Text\"*](http:\u002F\u002Fknowitall.cs.washington.edu\u002Fleibniz\u002Fpaper.pdf), published on EMNLP 2010.\n* [Entailment rules](http:\u002F\u002Fu.cs.biu.ac.il\u002F~nlp\u002Fresources\u002Fdownloads\u002Fpredicative-entailment-rules-learned-using-local-and-global-algorithms\u002F): 10M predicative entailment rules learned using local and global algorithms. From the documentation: \n  \"This resource of predicative entailment rules contains three resources in two formats – shallow and syntactic. Resources are learned over the REVERB data set and using the local and algorithms described in Chapter 5 of Jonathan Berant’s thesis (which is part of the package).\"\n* [Entailment rules](https:\u002F\u002Fgithub.com\u002Fdair-iitd\u002Fkglr): 36K high precision entailment rules (data and code). The resource is the result of the work of Prachi Jain and Mausam [*\"Knowledge-Guided Linguistic Rewrites for Inference Rule Verification\"*](http:\u002F\u002Fwww.cse.iitd.ac.in\u002F~mausam\u002Fpapers\u002Fnaacl16b.pdf) published on NAACL-HLT, 2016.\n\n### PhD theses\n\n* [*\"Compact Open Information Extraction: Methods, Corpora, Analysis\"*](https:\u002F\u002Fmadoc.bib.uni-mannheim.de\u002F59813\u002F1\u002Fthesis-kiril-gashteovski-final.pdf) by Kiril Gashteovski, University of Mannheim, Germany, 2020\n\n* [*\"Constructing Lexicons of Relational Phrases\"*](https:\u002F\u002Fpublikationen.sulb.uni-saarland.de\u002Fbitstream\u002F20.500.11880\u002F26789\u002F1\u002Fadam_grycner.pdf) by Adam Grycner, University of Saarland, Germany, 2017\n\n* [*\"Methods for open information extraction and sense disambiguation on natural language text\"*](https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~corrogg\u002Fpublications\u002Fdelcorro-thesis.pdf) by Luciano Del Corro, University of Saarland, Germany, 2016\n\n* [*\"Automated Knowledge Base Extension Using Open Information\"*](https:\u002F\u002Fub-madoc.bib.uni-mannheim.de\u002F40469\u002F1\u002Fdutta.dissertation.pdf) by Arnab Kumar Dutta, University of Mannheim, Germany, 2015\n\n* [*\"Exploiting Knowledge in Unsupervised Open Information Extraction\"*](https:\u002F\u002Fsearch.proquest.com\u002Fdocview\u002F1372164047?pq-origsite=gscholar) by Yuval Merhav, Illinois Institute of Technology, USA, 2012\n\n* [*\"Open Information Extraction for the Web\"*](http:\u002F\u002Fturing.cs.washington.edu\u002Fpapers\u002Fbanko-thesis.pdf) by Michele Banko, University of Washington, USA, 2009\n\n### Demos\n* [ClausIE:](https:\u002F\u002Fgate.d5.mpi-inf.mpg.de\u002FClausIEGate\u002FClausIEGate\u002F) Demo for ClausIE, an OIE system.\n* [Fact retrieval:](https:\u002F\u002Fopenie.allenai.org\u002F) Fact retrieval with OpenIE on large corpora.","# oie-resources 快速上手指南\n\n## 环境准备\n- **系统要求**：Windows\u002FmacOS\u002FLinux（支持 Git 的任意操作系统）\n- **前置依赖**：Git（[官方下载](https:\u002F\u002Fgit-scm.com\u002F)），推荐安装最新版\n- **网络建议**：国内用户优先使用 GitHub 镜像加速（推荐 `https:\u002F\u002Fghproxy.com\u002F` 代理服务）\n\n## 安装步骤\n克隆资源仓库到本地（自动使用国内镜像加速）：\n```bash\ngit clone https:\u002F\u002Fghproxy.com\u002Fhttps:\u002F\u002Fgithub.com\u002Folliegiese\u002Foie-resources.git\n```\n若镜像失效，可直接使用原始地址（访问可能较慢）：\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Folliegiese\u002Foie-resources.git\n```\n\n## 基本使用\n1. 进入项目目录：\n   ```bash\n   cd oie-resources\n   ```\n2. 查看核心资源列表（推荐用浏览器打开 `README.md`）：\n   ```bash\n   # Linux\u002FmacOS\n   open README.md\n   \n   # Windows\n   start README.md\n   ```\n3. **快速示例**：查找中文 OIE 系统  \n   在 `README.md` 中定位 `## OIE Systems for Chinese Language` 部分，即可获取中文开放关系抽取工具列表及资源链接。  \n   （注：该工具为资源索引库，无需额外运行命令，直接查阅文档即可获取论文\u002F代码\u002F数据集等资源）","某科技公司的NLP团队在开发实时中文新闻摘要系统时，需从海量新闻中精准提取\"公司-事件-地点\"等关系三元组，以构建动态知识图谱支撑摘要生成。\n\n### 没有 oie-resources 时\n- 团队成员耗费数周在零散平台（如Google Scholar、GitHub）手动筛选OIE论文和代码，常因关键词不匹配错过关键资源，延误项目进度。\n- 针对中文新闻处理，难以定位适配的OIE系统实现，主流英文工具（如TextRunner）在中文语境下错误率高达40%，导致关系提取失真。\n- 评估环节缺乏标准中文数据集和指标，团队自行标注测试集耗时费力，且结果无法与行业基准对比，影响模型优化方向。\n- 将OIE集成到摘要流程时，无成熟案例参考，反复调试参数导致开发周期延长两周以上。\n- 新工程师入职后需自行梳理庞杂文献，平均耗时1个月才能理解OIE技术脉络，拖累团队整体效率。\n\n### 使用 oie-resources 后\n- 通过oie-resources的\"Chronological Papers\"和\"Code\"板块，团队30分钟内获取近十年核心论文及开源实现（如ClausIE），快速锁定适合项目的轻量级模型。\n- 直接调用\"OIE Systems for Chinese Language\"部分的中文专用工具（如COpenIE），将中文关系提取准确率提升至75%，显著减少语义错误。\n- 借助\"Data\"中的标准中文语料库（如CAIL-OIE）和\"Evaluation\"指南，建立自动化评估流水线，模型迭代效率提高50%。\n- 参考\"Text Summarization\"应用案例，复用现成的集成方案（如结合BERT的摘要生成框架），一周内完成OIE模块对接。\n- 新成员通过\"PhD Theses\"和\"Slides\"资源，3天掌握OIE技术演进与实践要点，快速投入开发任务。\n\noie-resources让团队从资源搜寻的泥潭中解脱，将OIE技术落地周期缩短60%，真正释放信息抽取的生产力价值。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgkiril_oie-resources_dfa38237.png","gkiril","Kiril Gashteovski","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fgkiril_193c53a6.jpg","Research Scientist at NEC Labs Europe","NEC Laboratories Europe","Heidelberg, Germany","kiril.gashteovski@gmail.com","kgashteo",null,"https:\u002F\u002Fgithub.com\u002Fgkiril",503,58,"2026-04-02T08:38:06",1,"","未说明",{"notes":93,"python":91,"dependencies":94},"该仓库仅为开放信息抽取（OIE）资源列表索引，不包含可执行代码或具体工具实现，因此无运行环境需求。所有链接资源（如论文、代码库）的环境要求需参考各自项目文档。",[],[13,53,54,15,14,26,51],[97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"open-information-extraction","information-extraction","nlp","nlp-resources","nlp-apis","literature-review","papers","natural-language-processing","natural-language-understanding","nlu","oie-systems","extract-information","relation-extraction","openie","dataset","data-science","datascience","ai","big-data","corpus-data",4,"2026-03-27T02:49:30.150509","2026-04-06T08:46:06.158092",[],[]]