[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-IndexFziQ--GNN4NLP-Papers":3,"tool-IndexFziQ--GNN4NLP-Papers":65},[4,18,28,36,44,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":24,"last_commit_at":25,"category_tags":26,"status":17},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",150037,2,"2026-04-10T23:33:47",[14,13,27],"语言模型",{"id":29,"name":30,"github_repo":31,"description_zh":32,"stars":33,"difficulty_score":10,"last_commit_at":34,"category_tags":35,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[27,15,13,14],{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":24,"last_commit_at":42,"category_tags":43,"status":17},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",[14,27],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":24,"last_commit_at":50,"category_tags":51,"status":17},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。",85092,"2026-04-10T11:13:16",[15,16,52,53,13,54,27,14,55],"视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":62,"last_commit_at":63,"category_tags":64,"status":17},5784,"funNLP","fighting41love\u002FfunNLP","funNLP 是一个专为中文自然语言处理（NLP）打造的超级资源库，被誉为\"NLP 民工的乐园”。它并非单一的软件工具，而是一个汇集了海量开源项目、数据集、预训练模型和实用代码的综合性平台。\n\n面对中文 NLP 领域资源分散、入门门槛高以及特定场景数据匮乏的痛点，funNLP 提供了“一站式”解决方案。这里不仅涵盖了分词、命名实体识别、情感分析、文本摘要等基础任务的标准工具，还独特地收录了丰富的垂直领域资源，如法律、医疗、金融行业的专用词库与数据集，甚至包含古诗词生成、歌词创作等趣味应用。其核心亮点在于极高的全面性与实用性，从基础的字典词典到前沿的 BERT、GPT-2 模型代码，再到高质量的标注数据和竞赛方案，应有尽有。\n\n无论是刚刚踏入 NLP 领域的学生、需要快速验证想法的算法工程师，还是从事人工智能研究的学者，都能在这里找到急需的“武器弹药”。对于开发者而言，它能大幅减少寻找数据和复现模型的时间；对于研究者，它提供了丰富的基准测试资源和前沿技术参考。funNLP 以开放共享的精神，极大地降低了中文自然语言处理的开发与研究成本，是中文 AI 社区不可或缺的宝藏仓库。",79857,1,"2026-04-08T20:11:31",[27,16,54],{"id":66,"github_repo":67,"name":68,"description_en":69,"description_zh":70,"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":76,"owner_website":83,"owner_url":84,"languages":85,"stars":86,"forks":87,"last_commit_at":88,"license":89,"difficulty_score":90,"env_os":91,"env_gpu":92,"env_ram":92,"env_deps":93,"category_tags":96,"github_topics":97,"view_count":109,"oss_zip_url":85,"oss_zip_packed_at":85,"status":17,"created_at":110,"updated_at":111,"faqs":112,"releases":113},2882,"IndexFziQ\u002FGNN4NLP-Papers","GNN4NLP-Papers","A list of recent papers about Graph Neural Network methods applied in NLP areas.","GNN4NLP-Papers 是一个专注于收集与整理“图神经网络（GNN）在自然语言处理（NLP）领域应用”的最新学术论文清单。它旨在解决研究人员在面对海量文献时，难以快速定位高质量、前沿 GNN+NLP 交叉领域成果的痛点。\n\n该资源库系统性地收录了来自 ACL、EMNLP、NAACL、COLING、ICLR 等顶级会议的相关论文，覆盖了从基础任务（如词嵌入增强、语义角色标注）到文本分类、少样本学习等多个核心方向。其独特的技术亮点在于提供了清晰的分类体系（Taxonomy），并附带了部分论文的 PDF 链接和开源代码地址，甚至包含相关的博士论文，极大地提升了文献调研的效率。\n\nGNN4NLP-Papers 非常适合人工智能领域的研究人员、高校师生以及算法工程师使用。对于希望探索图结构数据如何提升语言模型性能的开发者，或是正在寻找特定任务（如命名实体识别、指代消解）解决方案的从业者，这里都是一份宝贵的入门指南和参考索引。通过持续更新的机制，它能帮助用户紧跟技术潮流，快速掌握该细分领域的研究动态。","# GNN4NLP-Papers\n![](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Latest-Commit&message=2022\u002F09\u002F20&color=important) ![](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Newest&message=COLING-2022&color=red)\n\nA list of recent papers about GNN methods applied in NLP areas. Now, the repository includes papers published at ACL, EMNLP, NAACL-HLT, COLING, ICLR, WWW, IJCAI, AAAI, NIPS, ICML, KDD, SIGIR and so on.\n\n- **New! Oct. 12, 2022:  Add COLING-2022!**\n\n- Sep. 20, 2022:  Add NAACL-2022\n\n- May. 23, 2022:  Add ACL-2022\n\n- Nov. 9, 2021:  Add EMNLP-2021\n\n- Jul. 28, 2021:  Add ACL-2021\n\n- May. 24, 2021:  Add NAACL-2021\n\n- Dec. 14, 2020:  Add COLING-2020\n\n- Dec. 01, 2020:  Add EMNLP-2020\n\n- Jun. 24, 2020:  Add ACL-2020, GNN tools, and Ph.D. thesis.\n\n## Taxonomy\n\n### Fundamental NLP Tasks\n\n1. **Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks**. *Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya and Partha Talukdar*. ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.04283)] [[code](http:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FWordGCN)]\n\n2. **A Lexicon-Based Graph Neural Network for Chinese NER**. *Tao Gui, Yicheng Zou and Qi Zhang.* ***EMNLP 2019*** [[pdf](http:\u002F\u002Fqizhang.info\u002Fpaper\u002Femnlp-2019.ner.pdf)]\n\n3. **Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution**. *Yinchuan Xu, Junlin Yang.* ***GBNLP@ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW19-3814.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fianycxu\u002FRGCN-with-BERT)]\n\n4. **Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph**. *Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang, Bowen Yu, Hongsong Zhu and Tingwen Liu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.140.pdf)]\n\n5. **Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing**. *Yi Chen, Jiayang Cheng, Haiyun Jiang, Lemao Liu, Haisong Zhang, Shuming Shi and Ruifeng Xu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.147.pdf)]\n\n6. **Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution**. *Irene Li, Linfeng Song, Kun Xu and Dong Yu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.199.pdf)]\n\n7. **Graph Pre-training for AMR Parsing and Generation**. *Xuefeng Bai, Yulong Chen and Yue Zhang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.415.pdf)]\n\n8. **Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings**. *Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang and Stan Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.561.pdf)]\n\n   \n\n### Text Classification\n\n1. **Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification**. *Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li.* ***EMNLP 2019*** [[pdf](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F74.pdf)]\n\n2. **Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes**. *Paulo Cavalin, Victor Henrique Alves Ribeiro, Ana Appel and Claudio Pinhanez*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.324.pdf)]\n\n3. **Text Graph Transformer for Document Classification**. *Haopeng Zhang and Jiawei Zhang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.668.pdf)]\n\n4. **Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network**. *Chen Lyu, Weijie Liu and Ping Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.485.pdf)]\n\n5. **Inductive Topic Variational Graph Auto-Encoder for Text Classification**. *Qianqian Xie, Jimin Huang, Pan Du, Min Peng and Jian-Yun Nie*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.333.pdf)]\n\n6. **Label-Specific Dual Graph Neural Network for Multi-Label Text Classification**. *Qianwen Ma, Chunyuan Yuan, Wei Zhou and Songlin Hu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.298.pdf)]\n\n7. **Cross-lingual Text Classification with Heterogeneous Graph Neural Network**. *Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu and Zhisheng Wang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.78.pdf)]\n\n8. **Weakly-supervised Text Classification Based on Keyword Graph**. *Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu and Shuigeng Zhou*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.222.pdf)]\n\n9. **Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification**. *Yaqing Wang, Song Wang, Quanming Yao and Dejing Dou*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.247.pdf)]\n\n10. **Deep Attention Diffusion Graph Neural Networks for Text Classification**. *Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang and Xiaoyue Feng*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.642.pdf)]\n\n11. **Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP**. *Lukas Galke and Ansgar Scherp*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.279.pdf)]\n\n12. **Entailment Graph Learning with Textual Entailment and Soft Transitivity**. *Zhibin Chen, Yansong Feng and Dongyan Zhao*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.406.pdf)]\n\n\n### Sentiment Analysis\n\n1. **Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks**. *Chen Zhang, Qiuchi Li and Dawei Song.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03477)] [[code](https:\u002F\u002Fgithub.com\u002FGeneZC\u002FASGCN)]\n\n2. **Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis**. *Wenxuan Shi, Fei Li, Jingye Li, Hao Fei and Donghong Ji*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.291.pdf)]\n\n3. **Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks**. *Binxuan Huang and Kathleen M. Carley.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.02606)]\n\n4. **Relational Graph Attention Network for Aspect-based Sentiment Analysis**. *Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12362.pdf)] \n\n5. **Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification**. *Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang and Houfeng Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.69.pdf)]\n\n6. **Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification**. *Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He and Bowen Zhou*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.229.pdf)]\n\n\n\n### Question Answering\n\n1. **BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering.** *Yu Cao, Meng Fang and Dacheng Tao.* ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1032.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fcaoyu1991\u002FBAG)]\n\n2. **Question Answering by Reasoning Across Documents with Graph Convolutional Networks**. *Nicola De Cao, Wilker Aziz and Ivan Titov.* ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1240.pdf)]\n\n3. **Cognitive Graph for Multi-Hop Reading Comprehension at Scale**. *Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang and Jie Tang.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05460)] [[code](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FCogQA)]\n\n4. **Dynamically Fused Graph Network for Multi-hop Reasoning**. *Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang and Yong Yu.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.06933)]\n\n5. **Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs**. *Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He and Bowen Zhou.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07374)]\n\n6. **DialogueGCN A Graph Convolutional Neural Network for Emotion Recognition in Conversation**. *Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya and Alexander Gelbukh.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11540)]\n\n7. **GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification.** *Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li and Maosong Sun.*  ***ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1085)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGEAR)]\n\n8. **Reasoning Over Semantic-Level Graph for Fact Checking.** *Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang and Jian Yin.*  ***Arxiv 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03745)]\n\n9. **Message Passing for Complex Question Answering over Knowledge Graphs**. *Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, Michael Cochez.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06917?context=cs.CL)]\n\n10. **Knowledge-aware Textual Entailment with Graph Atention Network**. *Daoyuan Chen , Yaliang Li , Min Yang , Hai-Tao Zheng , Ying Shen.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3357384.3358071)]\n\n11. **Fine-grained Fact Verification with Kernel Graph Attention Network**. *Zhenghao Liu, Chenyan Xiong, Maosong Sun, Zhiyuan Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09796.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n\n12. **Sequence-to-Sequence Knowledge Graph Completion and Question Answering**. *Apoorv Saxena, Adrian Kochsiek and Rainer Gemulla*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.201.pdf)]\n\n13. **KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering**. *Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang and Michael Zeng*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.340.pdf)]\n\n14. **AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension**. *Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun and Yuzhong Qu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.494.pdf)]\n\n   \n\n### Information Extraction\n\n1. **Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks**. *Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang and Huajun Chen*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1306.pdf)]\n\n2. **Attention Guided Graph Convolutional Networks for Relation Extraction**. *Zhijiang Guo, Yan Zhang and Wei Lu.* ***ACL 2019*** [[pdf](http:\u002F\u002Fwww.statnlp.org\u002Fpaper\u002F2019\u002Fattention-guided-graph-convolutional-networks-relation-extraction.html)] [[code](https:\u002F\u002Fgithub.com\u002FCartus\u002FAGGCN_TACRED)]\n\n3. **Graph Neural Networks with Generated Parameters for Relation Extraction**. *Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua and Maosong Sun.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00756)]\n\n4. **GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction**. *Tsu-Jui Fu, Peng-Hsuan Li and Wei-Yun Ma*. ***ACL 2019*** [[pdf](https:\u002F\u002Ftsujuifu.github.io\u002Fprojs\u002Facl19_graph-rel.html)] [[code](https:\u002F\u002Fgithub.com\u002Ftsujuifu\u002Fpytorch_graph-rel)]\n\n5. **Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction**. *Hao Chen, Zepeng Zhai, Fangxiang Feng, Ruifan Li and Xiaojie Wang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.212.pdf)]\n\n   \n\n### Text Generation\n\n1. **Text Generation from Knowledge Graphs with Graph Transformers**. *Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata and Hannaneh Hajishirzi*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1238.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Frikdz\u002FGraphWriter)]\n\n2. **Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model**. *Wei Li, Jingjing Xu, Yancheng He, Shengli Yan, Yunfang Wu and Xu Sun.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.01231)] [[code](https:\u002F\u002Fgithub.com\u002Flancopku\u002FGraph-to-seq-comment-generation)]\n\n3. **Enhancing AMR-to-Text Generation with Dual Graph Representations**. *Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.00352)]\n\n4. **Heterogeneous Graph Neural Networks for Extractive Document Summarization**. *Danqing Wang, Pengfei Liu, Yining Zheng, Xipeng Qiu, Xuanjing Huang*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12393.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fbrxx122\u002FHeterSUMGraph)]\n\n5. **Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning**. *Swarnadeep Saha, Prateek Yadav and Mohit Bansal*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.85.pdf)]\n\n6. **Graph Enhanced Contrastive Learning for Radiology Findings Summarization**. *Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan and Tsung-Hui Chang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.320.pdf)]\n\n\n### Dialogue\n\n1. **Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking**. *Yue Feng, Aldo Lipani, Fanghua Ye, Qiang Zhang and Emine Yilmaz*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.10.pdf)]\n\n2. **HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations**. *Jia-Chen Gu, Chao-Hong Tan, Chongyang Tao, Zhen-Hua Ling, Huang Hu, Xiubo Geng and Daxin Jiang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.349.pdf)]\n\n3. **Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation**. *Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Yajing Sun, Yunpeng Li*. ***IJCAI 2022*** [[pdf](http:\u002F\u002Farxiv.org\u002Fabs\u002F2204.12749)]\n   \n\n### Knowledge Graph\n\n1. **Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks**. *Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao and Christos Faloutsos.* ***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Festimating-node-importance-in-knowledge-graphs-using-graph-neural-networks)]\n\n2. **Hashing Graph Convolution for Node Classification**. *Wenting Zhao, Zhen Cui, Chunyan Xu, Chengzheng Li, Tong Zhang，Jian Yang.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Feasychair.org\u002Fpublications\u002Fpreprint\u002FlhT3)]\n\n3. **Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment**. *Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun and Wei Wang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.36.pdf)]\n\n4. **Efficient Hyper-parameter Search for Knowledge Graph Embedding**. *Yongqi Zhang, Zhanke Zhou, Quanming Yao and Yong Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.194.pdf)]\n\n5. **CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion**. *Guanglin Niu, Bo Li, Yongfei Zhang and Shiliang Pu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.205.pdf)]\n\n6. **SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models**. *Liang Wang, Wei Zhao, Zhuoyu Wei and Jingming Liu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.295.pdf)]\n\n7. **RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion**. *Kai Chen, Ye Wang, Yitong Li and Aiping Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.402.pdf)]\n\n8. **Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning**. *Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo and Xueqi Cheng*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-short.32.pdf)]\n    \n\n### Abnormal Text Detection\n\n1. **Abusive Language Detection with Graph Convolutional Networks**. *Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis and Ekaterina Shutova*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1221.pdf)]\n\n2. **Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media**. *Chang Li and Dan Goldwasser*. ***ACL 2019*** [[pdf](https:\u002F\u002Fwww.cs.purdue.edu\u002Fhomes\u002Fdgoldwas\u002F\u002Fdownloads\u002Fpapers\u002FLiG_acl_2019.pdf)]\n\n3. **Spam Review Detection with Graph Convolutional Networks**. *Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, Dong Li.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10679v1)]\n\n4. **Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion**. *Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, Gerhard Weikum.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03262v1)]\n\n5. **GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media**. *Yi-Ju Lu, Cheng-Te Li*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.11648.pdf)]\n\n6. **Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural Networks**. *Nikhil Mehta, Maria Pacheco and Dan Goldwasser*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.97.pdf)]\n\n    \n\n### Visual Question Answering\n\n1. **Relation-Aware Graph Attention Network for Visual Question Answering**. *Linjie Li, Zhe Gan, Yu Cheng and Jingjing Liu.* ***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.12314)]\n\n2. **Language-Conditioned Graph Networks for Relational Reasoning**. *Ronghang Hu, Anna Rohrbach, Trevor Darrell and Kate Saenko.* ***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.04405)] [[code](http:\u002F\u002Fronghanghu.com\u002Flcgn)]\n\n3. **Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension**. *Daesik Kim, Seonhoon Kim and Nojun Kwak.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.00232)]\n\n4. **Aligned Dual Channel Graph Convolutional Network for Visual Question Answering**. *Qingbao Huang, Jielong Wei, Yi Cai, Changmeng Zheng, Junying Chen, Ho-fung Leung, Qing Li*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.642.pdf)] \n\n5. **Multimodal Neural Graph Memory Networks for Visual Question Answering**. *Mahmoud Khademi*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.643.pdf)] \n\n6. **Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension**. *Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei and Zhenglu Yang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.84.pdf)]\n\n7. **Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network**. *Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei and Ruifeng Xu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.124.pdf)]\n\n    \n\n### Theory\n\n1. **HetGNN: Heterogeneous Graph Neural Network**. *Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami and Nitesh V. Chawla.* ***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Fhetgnn-heterogeneous-graph-neural-network)]\n\n2. **GMNN: Graph Markov Neural Networks**. *Meng Qu, Yoshua Bengio and  Jian Tang.* ***ICML 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.06214.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FGMNN)]\n\n3. **Unsupervised Dependency Graph Network**. *Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou and Aaron Courville*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.327.pdf)]\n\n\n\n## According to Conference\n\n***NAACL-HLT 2019***\n\n1. **BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering.** *Yu Cao, Meng Fang and Dacheng Tao.* ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1032.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fcaoyu1991\u002FBAG)]\n2. **Abusive Language Detection with Graph Convolutional Networks**. *Pushkar Mishra, Marco Del Tredici, Helen Yannakoudakis and Ekaterina Shutova*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1221.pdf)]\n3. **Text Generation from Knowledge Graphs with Graph Transformers**. *Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata and Hannaneh Hajishirzi*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1238.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Frikdz\u002FGraphWriter)]\n4. **Question Answering by Reasoning Across Documents with Graph Convolutional Networks**. *Nicola De Cao, Wilker Aziz and Ivan Titov.* ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1240.pdf)]\n5. **Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks**. *Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang and Huajun Chen*. ***NAACL-HLT 2019***. [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1306.pdf)]\n\n   \n\n***KDD 2019***\n\n1. **Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks**. *Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao and Christos Faloutsos.* ***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Festimating-node-importance-in-knowledge-graphs-using-graph-neural-networks)]\n2. **HetGNN: Heterogeneous Graph Neural Network**. *Chuxu Zhang, Dongjin Song, Chao Huang, Ananthram Swami and Nitesh V. Chawla.* ***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Fhetgnn-heterogeneous-graph-neural-network)]\n\n   \n\n***ICML 2019***\n\n1. **GMNN: Graph Markov Neural Networks**. *Meng Qu, Yoshua Bengio and  Jian Tang.* ***ICML 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.06214.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FGMNN)]\n\n   \n\n***ICCV 2019***\n\n1. **Relation-Aware Graph Attention Network for Visual Question Answering**. *Linjie Li, Zhe Gan, Yu Cheng and Jingjing Liu.* ***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.12314)]\n2. **Language-Conditioned Graph Networks for Relational Reasoning**. *Ronghang Hu, Anna Rohrbach, Trevor Darrell and Kate Saenko.* ***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.04405)] [[code](http:\u002F\u002Fronghanghu.com\u002Flcgn)]\n\n\n\n***ACL 2019***\n\n1. **Attention Guided Graph Convolutional Networks for Relation Extraction**. *Zhijiang Guo, Yan Zhang and Wei Lu.* ***ACL 2019*** [[pdf](http:\u002F\u002Fwww.statnlp.org\u002Fpaper\u002F2019\u002Fattention-guided-graph-convolutional-networks-relation-extraction.html)] [[code](https:\u002F\u002Fgithub.com\u002FCartus\u002FAGGCN_TACRED)]\n2. **GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification.** *Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li and Maosong Sun.* ***ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1085)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGEAR)]\n3. **Cognitive Graph for Multi-Hop Reading Comprehension at Scale**. *Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang and Jie Tang.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05460)] [[code](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FCogQA)]\n4. **Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model**. *Wei Li, Jingjing Xu, Yancheng He, Shengli Yan, Yunfang Wu and Xu Sun.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.01231)] [[code](https:\u002F\u002Fgithub.com\u002Flancopku\u002FGraph-to-seq-comment-generation)]\n5. **Dynamically Fused Graph Network for Multi-hop Reasoning**. *Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang and Yong Yu.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.06933)]\n6. **Encoding Social Information with Graph Convolutional Networks for Political Perspective Detection in News Media**. *Chang Li and Dan Goldwasser*. ***ACL 2019*** [[pdf](https:\u002F\u002Fwww.cs.purdue.edu\u002Fhomes\u002Fdgoldwas\u002F\u002Fdownloads\u002Fpapers\u002FLiG_acl_2019.pdf)]\n7. **Graph Neural Networks with Generated Parameters for Relation Extraction**. *Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua and Maosong Sun.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00756)]\n8. **Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks**. *Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya and Partha Talukdar*. ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.04283)] [[code](http:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FWordGCN)]\n9. **GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction**. *Tsu-Jui Fu, Peng-Hsuan Li and Wei-Yun Ma*. ***ACL 2019*** [[pdf](https:\u002F\u002Ftsujuifu.github.io\u002Fprojs\u002Facl19_graph-rel.html)] [[code](https:\u002F\u002Fgithub.com\u002Ftsujuifu\u002Fpytorch_graph-rel)]\n10. **Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs**. *Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He and Bowen Zhou.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07374)]\n11. **Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension**. *Daesik Kim, Seonhoon Kim and Nojun Kwak.* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.00232)]\n12. **Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution**. *Yinchuan Xu, Junlin Yang.* ***GBNLP@ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW19-3814.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fianycxu\u002FRGCN-with-BERT)]\n\n\n\n***EMNLP-IJCNLP 2019***\n\n1. **A Lexicon-Based Graph Neural Network for Chinese NER**. *Tao Gui, Yicheng Zou and Qi Zhang.* ***EMNLP 2019*** [[pdf](http:\u002F\u002Fqizhang.info\u002Fpaper\u002Femnlp-2019.ner.pdf)]\n2. **Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks**. *Chen Zhang, Qiuchi Li and Dawei Song.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03477)]\n3. **DialogueGCN A Graph Convolutional Neural Network for Emotion Recognition in Conversation**. *Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya and Alexander Gelbukh.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11540)]\n4. **Enhancing AMR-to-Text Generation with Dual Graph Representations**. *Leonardo F. R. Ribeiro, Claire Gardent and Iryna Gurevych.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.00352)]\n5. **Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification**. *Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li.* ***EMNLP 2019*** [[pdf](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F74.pdf)]\n6. **Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks**. *Binxuan Huang and Kathleen M. Carley.* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.02606)]\n\n\n\n***CIKM 2019***\n\n1. **Spam Review Detection with Graph Convolutional Networks**. *Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, Dong Li.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10679v1)]\n2. **Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction**. *Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, Liang Wang.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05552)] [[code](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FFi_GNNs)]\n3. **Message Passing for Complex Question Answering over Knowledge Graphs**. *Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, Michael Cochez.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06917?context=cs.CL)]\n4. **Knowledge-aware Textual Entailment with Graph Atention Network**. *Daoyuan Chen , Yaliang Li , Min Yang , Hai-Tao Zheng , Ying Shen.*  ***CIKM 2019*** [[pdf]()]\n5. **Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion**. *Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, Gerhard Weikum.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03262v1)]\n6. **Cross-domain Aspect Category Transfer and Detection via Traceable Heterogeneous Graph Representation Learning**. *Zhuoren Jiang, Jian Wang, Lujun Zhao, Changlong Sun, Yao Lu, Xiaozhong Liu.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11610)]\n7. **Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Commerce Recommendation**. *Fengli Xu , Jianxun Lian , Zhenyu Han , Yong Li , Yujian Xu , Xing Xie.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fuploads\u002Fprod\u002F2019\u002F09\u002FCIKM19-recogcn.pdf)]\n8. **Hashing Graph Convolution for Node Classification**. *Wenting Zhao, Zhen Cui, Chunyan Xu, Chengzheng Li, Tong Zhang，Jian Yang.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Feasychair.org\u002Fpublications\u002Fpreprint\u002FlhT3)]\n9. **Gravity-Inspired Graph Autoencoders for Directed Link Prediction**. *Guillaume Salha, Stratis Limnios, Romain Hennequin, Viet Anh Tran, Michalis Vazirgiannis.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09570)]\n10. **Multiple Rumor Source Detection with Graph Convolutional Networks**. *Ming Dong, Bolong Zheng, Nguyen Quoc Viet Hung, Han Su, Guohui Li.*  ***CIKM 2019*** [[pdf]()]\n\n\n\n***ICLR 2020***\n\n1. **Memory-based Graph Networks**. *Amir hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fpdf?id=r1laNeBYPB)]\n2. **InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization**. *Fan-Yun Sun, Jordan Hoffman, Vikas Verma, Jian Tang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1lfF2NYvH&noteId=r1lfF2NYvH)]\n3. **The Logical Expressiveness of Graph Neural Networks**. *Pablo Barceló, Egor V. Kostylev, Mikael Monet, Jorge Pérez, Juan Reutter, Juan Pablo Silva*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1lZ7AEKvB&noteId=r1lZ7AEKvB)]\n4. **Contrastive Learning of Structured World Models**. *Thomas Kipf, Elise van der Pol, Max Welling*. ***ICLR 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.12247)] [[code](https:\u002F\u002Fgithub.com\u002Ftkipf\u002Fc-swm)]\n5. **Geom-GCN: Geometric Graph Convolutional Networks**. *Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=S1e2agrFvS)]\n6. **Strategies for Pre-training Graph Neural Networks**. *Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=HJlWWJSFDH)]\n7. **Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning**. *Xiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, Zhi-Hong Deng*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=rkeuAhVKvB)]\n8. **What graph neural networks cannot learn: depth vs width**. *Andreas Loukas*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=B1l2bp4YwS)]\n9. **LambdaNet: Probabilistic Type Inference using Graph Neural Networks**. *Jiayi Wei, Maruth Goyal, Greg Durrett, Isil Dillig*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=Hkx6hANtwH)]\n10. **Graph Convolutional Reinforcement Learning**. *Jiechuan Jiang, Chen Dun, Tiejun Huang, Zongqing Lu*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=HkxdQkSYDB)]\n11. **DropEdge: Towards Deep Graph Convolutional Networks on Node Classification**. *Yu Rong, Wenbing Huang, Tingyang Xu, Junzhou Huang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=Hkx1qkrKPr)]\n12. **Efficient Probabilistic Logic Reasoning with Graph Neural Networks**. *Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=rJg76kStwH)]\n\n\n\n***WWW 2020***\n\n1. **TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network**. *Jiaming Shen, Zhihong Shen, Chenyan Xiong, Chi Wang, Kuansan Wang, Jiawei Han*. ***WWW 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.09522)]\n2. **Collective Multi-type Entity Alignment Between Knowledge Graphs**. *Qi Zhu, Hao Wei, Bunyamin Sisman, Da Zheng, Christos Faloutsos, Xin Luna Dong and Jiawei Han*. ***WWW 2020*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380289)]\n3. **Complex Factoid Question Answering with a Free-Text Knowledge Graph**. *Chen Zhao, Chenyan Xiong, Xin Qian and Jordan Boyd-Graber*. ***WWW 2020*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380197)]\n\n\n\n***ACL 2020***\n\n1. **Fine-grained Fact Verification with Kernel Graph Attention Network**. *Zhenghao Liu, Chenyan Xiong, Maosong Sun, Zhiyuan Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09796.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n2. **GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media**. *Yi-Ju Lu, Cheng-Te Li*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.11648.pdf)]\n3. **Heterogeneous Graph Neural Networks for Extractive Document Summarization**. *Danqing Wang, Pengfei Liu, Yining Zheng, Xipeng Qiu, Xuanjing Huang*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12393.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fbrxx122\u002FHeterSUMGraph)] \n4. **Relational Graph Attention Network for Aspect-based Sentiment Analysis**. *Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang*. ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12362.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fshenwzh3\u002FRGAT-ABSA)]\n5. **Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks**. *Yufeng Zhang∗ , Xueli Yu∗ , Zeyu Cui , Shu Wu, Zhongzhen Wen and Liang Wang*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.31.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FTextING)]\n6. **Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection**. *Lei Zhong, Juan Cao, Qiang Sheng, Junbo Guo, Ziang Wang*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.49.pdf)] [[code](http:\u002F\u002Fmcg.ict.ac.cn\u002Fcontroversy-detection-dataset.html)]\n7. **Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks**. *Yanbin Zhao, Lu Chen, Zhi Chen, Ruisheng Cao, Su Zhu, Kai Yu*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.67.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fybz79\u002FAMR2text)]\n8. **Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases**. *Yunshi Lan, Jing Jiang*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.91.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Flanyunshi\u002FMulti-hopComplexKBQA)]\n9. **Semantic Graphs for Generating Deep Questions**. *Liangming Pan, Yuxi Xie, Yansong Feng, Tat-Seng Chua, Min-Yen Kan*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.135.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FWING-NUS\u002FSG-Deep-Question-Generation)]\n10. **Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation**. *Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che , Ting Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.166.pdf)] \n11. **Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs**. *Houyu Zhang, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.184.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FConceptFlow)]\n12. **A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation**. *Yongjing Yin, Fandong Meng, Jinsong Su, Chulun Zhou, Zhengyuan Yang, Jie Zhou, Jiebo Luo*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.273.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FDeepLearnXMU\u002FGMNMT)]\n13. **Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks**. *Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.297.pdf)] \n14. **A Graph-based Coarse-to-fine Method for Unsupervised Bilingual Lexicon Induction**. *Shuo Ren, Shujie Liu, Ming Zhou, Shuai Ma*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.318.pdf)] \n15. **Graph Neural News Recommendation with Unsupervised Preference Disentanglement**. *Linmei Hu, Siyong Xu, Chen Li, Cheng Yang, Chuan Shi, Nan Duan, Xing Xie, Ming Zhou*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.392.pdf)] \n16. **Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward**. *Luyang Huang, Lingfei Wu and Lu Wang*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.457.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fluyang-huang96\u002FGraphAugmentedSum)]\n17. **Entity-Aware Dependency-Based Deep Graph Attention Network for Comparative Preference Classification**. *Nianzu Ma, Sahisnu Mazumder, Hao Wang, Bing Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.512.pdf)]\n18. **LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network**. *Wanjun Zhong , Duyu Tang, Zhangyin Feng , Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang and Jian Yin*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.539.pdf)] [[code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n19. **Reasoning Over Semantic-Level Graph for Fact Checking**. *Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang and Jian Yin*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.549.pdf)] \n20. **Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension**. *Bo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan, Wanxiang Che, Daxin Jiang, Ming Zhou and Ting Liu*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.599.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FDancingSoul\u002FNQ_BERT-DM)]\n21. **Heterogeneous Graph Transformer for Graph-to-Sequence Learning**. *Shaowei Yao, Tianming Wang, Xiaojun Wan*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.640.pdf)] [[code](https:\u002F\u002Fgithub.com\u002FQAQ-v\u002FHetGT)]\n22. **Aligned Dual Channel Graph Convolutional Network for Visual Question Answering**. *Qingbao Huang, Jielong Wei, Yi Cai, Changmeng Zheng, Junying Chen, Ho-fung Leung, Qing Li*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.642.pdf)] \n23. **Multimodal Neural Graph Memory Networks for Visual Question Answering**. *Mahmoud Khademi*. ***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.643.pdf)] \n\n\n***EMNLP 2020***\n\n1. **Connecting the Dots: Event Graph Schema Induction with Path Language Modeling**. *Manling Li, Qi Zeng, Ying Lin, Kyunghyun Cho, Heng Ji, Jonathan May, Nathanael Chambers and Clare Voss*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.50.pdf)]\n2. **Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph**. *Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, Xiaoyan Zhu and Minlie Huang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.54.pdf)]\n3. **Learning to Represent Image and Text with Denotation Graph**. *Bowen Zhang, Hexiang Hu, Vihan Jain, Eugene Ie and Fei Sha*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.60.pdf)]\n4. **ENT-DESC: Entity Description Generation by Exploring Knowledge Graph**. *Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu and Luo Si*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.90.pdf)]\n5. **Double Graph Based Reasoning for Document-level Relation Extraction**. *Shuang Zeng, Runxin Xu, Baobao Chang and Lei Li*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.127.pdf)]\n6. **Knowledge Graph Alignment with Entity-Pair Embedding**. *Zhichun Wang, Jinjian Yang and Xiaoju Ye*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.130.pdf)]\n7. **Adaptive Attentional Network for Few-Shot Knowledge Graph Completion**. *Jiawei Sheng, Shu Guo, Zhenyu Chen, Juwei Yue, Lihong Wang, Tingwen Liu and Hongbo Xu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.131.pdf)]\n8. **GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems**. *Shiquan Yang, Rui Zhang and Sarah Erfani*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.147.pdf)]\n9. **Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation**. *Yan Zhang, Zhijiang Guo, Zhiyang Teng, Wei Lu, Shay B. Cohen, Zuozhu Liu and Lidong Bing*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.169.pdf)]\n10. **Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages**. *Zheng Li, Mukul Kumar, William Headden, Bing Yin, Ying Wei, Yu Zhang and Qiang Yang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.179.pdf)]\n11. **Disentangle-based Continual Graph Representation Learning**. *Xiaoyu Kou, Yankai Lin, Shaobo Liu, Peng Li, Jie Zhou and Yan Zhang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.237.pdf)]\n12. **Learning Physical Common Sense as Knowledge Graph Completion via BERT Data Augmentation and Constrained Tucker Factorization**. *Zhenjie Zhao, Evangelos Papalexakis and Xiaojuan Ma*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.266.pdf)]\n13. **AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue**. *Jaehun Jung, Bokyung Son and Sungwon Lyu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.280.pdf)]\n14. **Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network**. *Ruipeng Jia, Yanan Cao, Hengzhu Tang, Fang Fang, Cong Cao and Shi Wang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.295.pdf)]\n15. **Neural Topic Modeling by Incorporating Document Relationship Graph**. *Deyu Zhou, Xuemeng Hu and Rui Wang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.310.pdf)]\n16. **Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling**. *Diego Marcheggiani and Ivan Titov*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.322.pdf)]\n17. **Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes**. *Paulo Cavalin, Victor Henrique Alves Ribeiro, Ana Appel and Claudio Pinhanez*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.324.pdf)]\n18. **Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit**. *Amrith Krishna, Ashim Gupta, Deepak Garasangi, Pavankumar Satuluri and Pawan Goyal*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.388.pdf)]\n19. **Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks**. *Viet Dac Lai, Tuan Ngo Nguyen and Thien Huu Nguyen*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.435.pdf)]\n20. **Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph**. *Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei Zhang, Yichi Zhang, Hao Kong and Suhui Wu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.459.pdf)]\n21. **Knowledge Association with Hyperbolic Knowledge Graph Embeddings**. *Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai and Wei Zhang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.460.pdf)]\n22. **TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion**. *Jiapeng Wu, Meng Cao, Jackie Chi Kit Cheung and William L. Hamilton*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.462.pdf)]\n23. **Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks**. *Yuanhe Tian, Yan Song and Fei Xia*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.487.pdf)]\n24. **Question Directed Graph Attention Network for Numerical Reasoning over Text**. *Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi and Wei Chu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.549.pdf)]\n25. **IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation**. *Yitao Cai and Xiaojun Wan*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.560.pdf)]\n26. **Is Graph Structure Necessary for Multi-hop Question Answering?**. *Nan Shao, Yiming Cui, Ting Liu, Shijin Wang and Guoping Hu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.583.pdf)]\n27. **DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion**. *Zhen Han, Peng Chen, Yunpu Ma and Volker Tresp*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.593.pdf)]\n28. **Embedding Words in Non-Vector Space with Unsupervised Graph Learning**. *Max Ryabinin, Sergei Popov, Liudmila Prokhorenkova and Elena Voita*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.594.pdf)]\n29. **Debiasing knowledge graph embeddings**. *Joseph Fisher, Arpit Mittal, Dave Palfrey and Christos Christodoulopoulos*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.595.pdf)]\n30. **Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations**. *Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki and Jun Goto*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.597.pdf)]\n31. **Program Enhanced Fact Verification with Verbalization and Graph Attention Network**. *Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen and Xiaodan Zhu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.628.pdf)]\n32. **VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls**. *Ramit Sawhney, Piyush Khanna, Arshiya Aggarwal, Taru Jain, Puneet Mathur and Rajiv Ratn Shah*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.643.pdf)]\n33. **Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction**. *Tara Safavi, Danai Koutra and Edgar Meij*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.667.pdf)]\n34. **Text Graph Transformer for Document Classification**. *Haopeng Zhang and Jiawei Zhang*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.668.pdf)]\n35. **CoDEx: A Comprehensive Knowledge Graph Completion Benchmark**. *Tara Safavi and Danai Koutra*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.669.pdf)]\n36. **Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning**. *Deren Lei, Gangrong Jiang, Xiaotao Gu, Kexuan Sun, Yuning Mao and Xiang Ren*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.688.pdf)]\n37. **Hierarchical Graph Network for Multi-hop Question Answering**. *Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang and Jingjing Liu*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.710.pdf)]\n38. **SRLGRN: Semantic Role Labeling Graph Reasoning Network**. *Chen Zheng and Parisa Kordjamshidi*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.714.pdf)]\n39. **LibKGE - A knowledge graph embedding library for reproducible research**. *Samuel Broscheit, Daniel Ruffinelli, Adrian Kochsiek, Patrick Betz and Rainer Gemulla*. ***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-demos.22.pdf)]\n\n\n***COLING 2020***\n\n1. **A Graph Representation of Semi-structured Data for Web Question Answering**. *Xingyao Zhang, Linjun Shou, Jian Pei, Ming Gong, Lijie Wen and Daxin Jiang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.5.pdf)]\n2. **Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis**. *Bin Liang, Rongdi Yin, Lin Gui, Jiachen Du and Ruifeng Xu*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.13.pdf)]\n3. **End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network**. *Ying Chen, Wenjun Hou, Shoushan Li, Caicong Wu and Xiaoqiang Zhang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.17.pdf)]\n4. **Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks**. *Guimin Chen, Yuanhe Tian and Yan Song*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.24.pdf)]\n5. **Heterogeneous Graph Neural Networks to Predict What Happen Next**. *Jianming Zheng, Fei Cai, Yanxiang Ling and Honghui Chen*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.29.pdf)]\n6. **Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words**. *Lulu Zhao, Weiran Xu and Jun Guo*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.39.pdf)]\n7. **AprilE: Attention with Pseudo Residual Connection for Knowledge Graph Embedding**. *Yuzhang Liu, Peng Wang, Yingtai Li, Yizhan Shao and Zhongkai Xu*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.44.pdf)]\n8. **Knowledge Graph Embeddings in Geometric Algebras**. *Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen and Jens Lehmann*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.46.pdf)]\n9. **Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization**. *Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald and Yunyao Li*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.47.pdf)]\n10. **RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion**. *Hao Huang, Guodong Long, Tao Shen, Jing Jiang and Chengqi Zhang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.48.pdf)]\n11. **Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification**. *Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang and Houfeng Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.69.pdf)]\n12. **Aspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network**. *Hongjie Cai, Yaofeng Tu, Xiangsheng Zhou, Jianfei Yu and Rui Xia*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.72.pdf)]\n13. **A High Precision Pipeline for Financial Knowledge Graph Construction**. *Sarah Elhammadi, Laks V.S. Lakshmanan, Raymond Ng, Michael Simpson, Baoxing Huai, Zhefeng Wang and Lanjun Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.84.pdf)]\n14. **R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning**. *Irene Li, Alexander Fabbri, Swapnil Hingmire and Dragomir Radev*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.99.pdf)]\n15. **Knowledge Graph Embedding with Atrous Convolution and Residual Learning**. *Feiliang Ren, Juchen Li, Huihui Zhang, Shilei Liu, Bochao Li, Ruicheng Ming and Yujia Bai*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.134.pdf)]\n16. **Graph Enhanced Dual Attention Network for Document-Level Relation Extraction**. *Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi and Shikun Zhang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.136.pdf)]\n17. **TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation**. *Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury, Hamed Shariat Yazdi and Jens Lehmann*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.139.pdf)]\n18. **Document-level Relation Extraction with Dual-tier Heterogeneous Graph**. *Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Tingwen Liu, Hengzhu Tang, Wang Yubin and Li Guo*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.143.pdf)]\n19. **Unsupervised Fact Checking by Counter-Weighted Positive and Negative Evidential Paths in A Knowledge Graph**. *Jiseong Kim and Key-sun Choi*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.147.pdf)]\n20. **Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models**. *Bosung Kim, Taesuk Hong, Youngjoong Ko and Jungyun Seo*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.153.pdf)]\n21. **Visual-Textual Alignment for Graph Inference in Visual Dialog**. *Tianling Jiang, Yi Ji, Chunping Liu and Hailin Shao*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.170.pdf)]\n22. **I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning**. *Jungwoo Lim, Dongsuk Oh, Yoonna Jang, Kisu Yang and Heuiseok Lim*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.222.pdf)]\n23. **Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph**. *Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao and Zhenzi Li*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.231.pdf)]\n24. **Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs**. *Wan-Hsuan Lin and Chun-Shien Lu*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.240.pdf)]\n25. **Syntactic Graph Convolutional Network for Spoken Language Understanding**. *Keqing He, Shuyu Lei, Yushu Yang, Huixing Jiang and Zhongyuan Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.246.pdf)]\n26. **Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition**. *Dongming Sheng, Dong Wang, Ying Shen, Haitao Zheng and Haozhuang Liu*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.367.pdf)]\n27. **Integrating User History into Heterogeneous Graph for Dialogue Act Recognition**. *Dong Wang, Ziran Li, Haitao Zheng and Ying Shen*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.372.pdf)]\n28. **Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity**. *Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang, Yu Zhou and Chengqing Zong*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.397.pdf)]\n29. **Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities**. *Hao Zhang, Jae Ro and Richard Sproat*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.411.pdf)]\n30. **Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction**. *Huiwei Zhou, Yibin Xu, Weihong Yao, Zhe Liu, Chengkun Lang and Haibin Jiang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.461.pdf)]\n31. **Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks**. *Peng Cui, Le Hu and Yuanchao Liu*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.468.pdf)]\n32. **Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network**. *Chen Lyu, Weijie Liu and Ping Wang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.485.pdf)]\n33. **Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT**. *Ruifeng Yuan, Zili Wang and Wenjie Li*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.493.pdf)]\n34. **A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment**. *Zhiwen Xie, Runjie Zhu, Kunsong Zhao, Jin Liu, Guangyou Zhou and Jimmy Xiangji Huang*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.520.pdf)]\n35. **Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction**. *Angrosh Mandya, Danushka Bollegala and Frans Coenen*. ***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.565.pdf)]\n\n\n***NAACL 2021***\n\n1. **Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks**. *Minh Van Nguyen, Viet Lai and Thien Huu Nguyen*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.3.pdf)]\n2. **Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction**. *Zixuan Zhang and Heng Ji*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.4.pdf)]\n3. **Event Time Extraction and Propagation via Graph Attention Networks**. *Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong and Dan Roth*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.6.pdf)]\n4. **SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation**. *Luigi Procopio, Rocco Tripodi and Roberto Navigli*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.30.pdf)]\n5. **Neural Language Modeling for Contextualized Temporal Graph Generation**. *Aman Madaan and Yiming Yang*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.67.pdf)]\n6. **Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning**. *Xuelu Chen, Michael Boratko, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li and Andrew McCallum*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.68.pdf)]\n7. **MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences**. *Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria and Louis-Philippe Morency*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.79.pdf)]\n8. **Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network**. *Fan Jiang and Trevor Cohn*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.125.pdf)]\n9. **Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network**. *Haoran Wu, Wei Chen, Shuang Xu and Bo Xu*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.156.pdf)]\n10. **Generating An Optimal Interview Question Plan Using A Knowledge Graph And Integer Linear Programming**. *Soham Datta, Prabir Mallick, Sangameshwar Patil, Indrajit Bhattacharya and Girish Palshikar*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.160.pdf)]\n11. **Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data**. *Chenghao Jia, Yongliang Shen, Yechun Tang, Lu Sun and Weiming Lu*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.164.pdf)]\n12. **Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis**. *Xutan Peng, Guanyi Chen, Chenghua Lin and Mark Stevenson*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.187.pdf)]\n13. **Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings**. *Chengjin Xu, Yung-Yu Chen, Mojtaba Nayyeri and Jens Lehmann*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.202.pdf)]\n14. **Edge: Enriching Knowledge Graph Embeddings with External Text**. *Saed Rezayi, Handong Zhao, Sungchul Kim, Ryan Rossi, Nedim Lipka and Sheng Li*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.221.pdf)]\n15. **Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification**. *Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He and Bowen Zhou*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.229.pdf)]\n16. **Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble**. *Yuanhe Tian, Guimin Chen and Yan Song*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.231.pdf)]\n17. **Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures**. *Minh Tran Phu and Thien Huu Nguyen*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.273.pdf)]\n18. **Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training**. *Oshin Agarwal, Heming Ge, Siamak Shakeri and Rami Al-Rfou*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.278.pdf)]\n19. **Inductive Topic Variational Graph Auto-Encoder for Text Classification**. *Qianqian Xie, Jimin Huang, Pan Du, Min Peng and Jian-Yun Nie*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.333.pdf)]\n20. **Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters**. *Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi and Markus Dreyer*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.380.pdf)]\n21. **Modeling Human Mental States with an Entity-based Narrative Graph**. *I-Ta Lee, Maria Leonor Pacheco and Dan Goldwasser*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.391.pdf)]\n22. **ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser**. *Zhi Chen, Lu Chen, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu and Kai Yu*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002Fhttps:\u002F\u002Fgithub.com\u002FWowCZ\u002Fshadowgnn.pdf)]\n23. **RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion**. *Youri Xu, Haihong E, Meina Song, Wenyu Song, Xiaodong Lv, Wang Haotian and Yang Jinrui*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.451.pdf)]\n24. **Breadth First Reasoning Graph for Multi-hop Question Answering**. *Yongjie Huang and Meng Yang*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.464.pdf)]\n25. **Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph**. *Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang and Daxin Jiang*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.465.pdf)]\n26. **DAGN: Discourse-Aware Graph Network for Logical Reasoning**. *Yinya Huang, Meng Fang, Yu Cao, Liwei Wang and Xiaodan Liang*. ***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.467.pdf)]\n\n***ACL 2021***\n\n1. **Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks**. *Xiaocui Yang, Shi Feng, Yifei Zhang and Daling Wang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.28.pdf)]\n2. **SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues**. *Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu and Song-Chun Zhu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.54.pdf)]\n3. **CitationIE: Leveraging the Citation Graph for Scientific Information Extraction**. *Vijay Viswanathan, Graham Neubig and Pengfei Liu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.59.pdf)]\n4. **Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge**. *Linmei Hu, Tianchi Yang, Luhao Zhang, Wanjun Zhong, Duyu Tang, Chuan Shi, Nan Duan and Ming Zhou*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.62.pdf)]\n6. **Directed Acyclic Graph Network for Conversational Emotion Recognition**. *Weizhou Shen, Siyue Wu, Yunyi Yang and Xiaojun Quan*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.123.pdf)]\n7. **Discovering Dialog Structure Graph for Coherent Dialog Generation**. *Jun Xu, Zeyang Lei, Haifeng Wang, Zheng-Yu Niu, Hua Wu and Wanxiang Che*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.136.pdf)]\n8. **Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach**. *Yifan Hou and Mrinmaya Sachan*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.145.pdf)]\n9. **Poisoning Knowledge Graph Embeddings via Relation Inference Patterns**. *Peru Bhardwaj, John Kelleher, Luca Costabello and Declan O’Sullivan*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.147.pdf)]\n10. **ExCAR: Event Graph Knowledge Enhanced Explainable Causal Reasoning**. *Li Du, Xiao Ding, Kai Xiong, Ting Liu and Bing Qin*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.183.pdf)]\n11. **LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations**. *Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu and Kai Yu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.198.pdf)]\n12. **Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment**. *Xinying Qiu, Yuan Chen, Hanwu Chen, Jian-Yun Nie, Yuming Shen and Dawei Lu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.235.pdf)]\n13. **Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction**. *Hanqi Yan, Lin Gui, Gabriele Pergola and Yulan He*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.261.pdf)]\n14. **Structured Sentiment Analysis as Dependency Graph Parsing**. *Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid and Erik Velldal*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.263.pdf)]\n15. **Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection**. *Lingwei Wei, Dou Hu, Wei Zhou, Zhaojuan Yue and Songlin Hu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.297.pdf)]\n16. **Label-Specific Dual Graph Neural Network for Multi-Label Text Classification**. *Qianwen Ma, Chunyuan Yuan, Wei Zhou and Songlin Hu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.298.pdf)]\n17. **ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences**. *Yanjun Gao, Ting-Hao Huang and Rebecca J. Passonneau*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.303.pdf)]\n18. **Psycholinguistic Tripartite Graph Network for Personality Detection**. *Tao Yang, Feifan Yang, Haolan Ouyang and Xiaojun Quan*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.326.pdf)]\n19. **PairRE: Knowledge Graph Embeddings via Paired Relation Vectors**. *Linlin Chao, Jianshan He, Taifeng Wang and Wei Chu*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.336.pdf)]\n20. **Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks**. *Yuanhe Tian, Guimin Chen, Yan Song and Xiang Wan*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.344.pdf)]\n21. **How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction**. *Zikun Hu, Yixin Cao, Lifu Huang and Tat-Seng Chua*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.359.pdf)]\n22. **Reasoning over Entity-Action-Location Graph for Procedural Text Understanding**. *Hao Huang, Xiubo Geng, Jian Pei, Guodong Long and Daxin Jiang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.396.pdf)]\n23. **Learning Event Graph Knowledge for Abductive Reasoning**. *Li Du, Xiao Ding, Ting Liu and Bing Qin*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.403.pdf)]\n24. **Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding**. *Hidetaka Kamigaito and Katsuhiko Hayashi*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.429.pdf)]\n25. **MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation**. *Jingwen Hu, Yuchen Liu, Jinming Zhao and Qin Jin*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.440.pdf)]\n26. **BASS: Boosting Abstractive Summarization with Unified Semantic Graph**. *Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu and Haifeng Wang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.472.pdf)]\n27. **Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis**. *Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang and Eduard Hovy*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.494.pdf)]\n28. **Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning**. *Shuoran Jiang, Qingcai Chen, Xin Liu, Baotian Hu and Lisai Zhang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.513.pdf)]\n30. **Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer**. *Fabian Galetzka, Jewgeni Rose, David Schlangen and Jens Lehmann*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.546.pdf)]\n31. **Cross-lingual Text Classification with Heterogeneous Graph Neural Network**. *Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu and Zhisheng Wang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.78.pdf)]\n32. **Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations**. *Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Kartik Talamadupula, Mrinmaya Sachan and Murray Campbell*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.91.pdf)]\n33. **Explicitly Capturing Relations between Entity Mentions via Graph Neural Networks for Domain-specific Named Entity Recognition**. *Pei Chen, Haibo Ding, Jun Araki and Ruihong Huang*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.93.pdf)]\n34. **Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders**. *Irene Li, Vanessa Yan, Tianxiao Li, Rihao Qu and Dragomir Radev*. ***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.127.pdf)]\n\n***EMNLP 2021***\n\n1. **Multiplex Graph Neural Network for Extractive Text Summarization**. *Baoyu Jing, Zeyu You, Tao Yang, Wei Fan and Hanghang Tong*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.11.pdf)]\n2. **Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge**. *Bin Liang, Hang Su, Rongdi Yin, Lin Gui, Min Yang, Qin Zhao, Xiaoqi Yu and Ruifeng Xu*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.19.pdf)]\n3. **Graph Based Network with Contextualized Representations of Turns in Dialogue**. *Bongseok Lee and Yong Suk Choi*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.36.pdf)]\n4. **Extend, don’t rebuild: Phrasing conditional graph modification as autoregressive sequence labelling**. *Leon Weber, Jannes Münchmeyer, Samuele Garda and Ulf Leser*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.93.pdf)]\n5. **CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation**. *Wenchang Ma, Ryuichi Takanobu and Minlie Huang*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.139.pdf)]\n6. **CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling**. *Han Wu, Kun Xu and Linqi Song*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.177.pdf)]\n7. **Building the Directed Semantic Graph for Coherent Long Text Generation**. *Ziao Wang, Xiaofeng Zhang and Hongwei Du*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.200.pdf)]\n8. **Heterogeneous Graph Neural Networks for Keyphrase Generation**. *Jiacheng Ye, Ruijian Cai, Tao Gui and Qi Zhang*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.213.pdf)]\n9. **Weakly-supervised Text Classification Based on Keyword Graph**. *Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu and Shuigeng Zhou*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.222.pdf)]\n10. **Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification**. *Yaqing Wang, Song Wang, Quanming Yao and Dejing Dou*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.247.pdf)]\n11. **GraphMR: Graph Neural Network for Mathematical Reasoning**. *Weijie Feng, Binbin Liu, Dongpeng Xu, Qilong Zheng and Yun Xu*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.273.pdf)]\n12. **Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph**. *Jianzhu Bao, Bin Liang, Jingyi Sun, Yice Zhang, Min Yang and Ruifeng Xu*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.319.pdf)]\n13. **Event Graph based Sentence Fusion**. *Ruifeng Yuan, Zili Wang and Wenjie Li*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.334.pdf)]\n14. **TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph**. *Jiaxin Shi, Shulin Cao, Lei Hou, Juanzi Li and Hanwang Zhang*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.341.pdf)]\n17. **The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction**. *Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han and Clare Voss*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.422.pdf)]\n20. **Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport**. *Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji and Kathleen McKeown*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.519.pdf)]\n21. **ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning**. *Swarnadeep Saha, Prateek Yadav, Lisa Bauer and Mohit Bansal*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.609.pdf)]\n24. **Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement**. *Mengting Hu, Honglei Guo, Shiwan Zhao, Hang Gao and Zhong Su*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.641.pdf)]\n25. **Deep Attention Diffusion Graph Neural Networks for Text Classification**. *Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang and Xiaoyue Feng*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.642.pdf)]\n28. **Document Graph for Neural Machine Translation**. *Mingzhou Xu, Liangyou Li, Derek F. Wong, Qun Liu and Lidia S. Chao*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.663.pdf)]\n29. **Graph Algorithms for Multiparallel Word Alignment**. *Ayyoob ImaniGooghari, Masoud Jalili Sabet, Lutfi Kerem Senel, Philipp Dufter, François Yvon and Hinrich Schütze*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.665.pdf)]\n31. **A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing**. *Chunchuan Lyu, Shay B. Cohen and Ivan Titov*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.714.pdf)]\n34. **Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks**. *Hongzhan Lin, Jing Ma, Mingfei Cheng, Zhiwei Yang, Liangliang Chen and Guang Chen*. ***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.786.pdf)]\n\n\n***ACL 2022***\n\n1. **Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking**. *Yue Feng, Aldo Lipani, Fanghua Ye, Qiang Zhang and Emine Yilmaz*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.10.pdf)]\n2. **Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment**. *Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun and Wei Wang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.36.pdf)]\n4. **Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension**. *Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei and Zhenglu Yang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.84.pdf)]\n5. **Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning**. *Swarnadeep Saha, Prateek Yadav and Mohit Bansal*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.85.pdf)]\n6. **Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural Networks**. *Nikhil Mehta, Maria Pacheco and Dan Goldwasser*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.97.pdf)]\n7. **Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network**. *Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei and Ruifeng Xu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.124.pdf)]\n8. **Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph**. *Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang, Bowen Yu, Hongsong Zhu and Tingwen Liu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.140.pdf)]\n9. **Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing**. *Yi Chen, Jiayang Cheng, Haiyun Jiang, Lemao Liu, Haisong Zhang, Shuming Shi and Ruifeng Xu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.147.pdf)]\n10. **Efficient Hyper-parameter Search for Knowledge Graph Embedding**. *Yongqi Zhang, Zhanke Zhou, Quanming Yao and Yong Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.194.pdf)]\n11. **Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution**. *Irene Li, Linfeng Song, Kun Xu and Dong Yu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.199.pdf)]\n12. **Sequence-to-Sequence Knowledge Graph Completion and Question Answering**. *Apoorv Saxena, Adrian Kochsiek and Rainer Gemulla*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.201.pdf)]\n13. **CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion**. *Guanglin Niu, Bo Li, Yongfei Zhang and Shiliang Pu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.205.pdf)]\n14. **Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction**. *Hao Chen, Zepeng Zhai, Fangxiang Feng, Ruifan Li and Xiaojie Wang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.212.pdf)]\n15. **Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP**. *Lukas Galke and Ansgar Scherp*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.279.pdf)]\n16. **Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis**. *Wenxuan Shi, Fei Li, Jingye Li, Hao Fei and Donghong Ji*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.291.pdf)]\n17. **SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models**. *Liang Wang, Wei Zhao, Zhuoyu Wei and Jingming Liu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.295.pdf)]\n18. **Graph Enhanced Contrastive Learning for Radiology Findings Summarization**. *Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan and Tsung-Hui Chang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.320.pdf)]\n19. **Unsupervised Dependency Graph Network**. *Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie Zhou and Aaron Courville*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.327.pdf)]\n20. **KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering**. *Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang and Michael Zeng*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.340.pdf)]\n21. **HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations**. *Jia-Chen Gu, Chao-Hong Tan, Chongyang Tao, Zhen-Hua Ling, Huang Hu, Xiubo Geng and Daxin Jiang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.349.pdf)]\n22. **RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion**. *Kai Chen, Ye Wang, Yitong Li and Aiping Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.402.pdf)]\n23. **Entailment Graph Learning with Textual Entailment and Soft Transitivity**. *Zhibin Chen, Yansong Feng and Dongyan Zhao*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.406.pdf)]\n24. **Graph Pre-training for AMR Parsing and Generation**. *Xuefeng Bai, Yulong Chen and Yue Zhang*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.415.pdf)]\n25. **AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension**. *Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun and Yuzhong Qu*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.494.pdf)]\n26. **Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings**. *Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang and Stan Li*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.561.pdf)]\n27. **Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning**. *Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo and Xueqi Cheng*. ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-short.32.pdf)]\n28. **CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge**. *Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen and Jun Zhao*. ***ACL Demo 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-demo.16.pdf)]\n29. **MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities**. *Yubo Ma, Zehao Wang, Mukai Li, Yixin Cao, Meiqi Chen, Xinze Li, Wenqi Sun, Kunquan Deng, Kun Wang, Aixin Sun and Jing Shao*. ***ACL Demo 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-demo.23.pdf)]\n\n\n***NAACL 2022***\n1. **Cross-document Misinformation Detection based on Event Graph Reasoning**. *Xueqing Wu, Kung-Hsiang Huang, Yi Fung and Heng Ji*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.40.pdf)]\n2. **DocTime: A Document-level Temporal Dependency Graph Parser**. *Puneet Mathur, Vlad Morariu, Verena Kaynig-Fittkau, Jiuxiang Gu, Franck Dernoncourt, Quan Tran, Ani Nenkova, Dinesh Manocha and Rajiv Jain*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.73.pdf)]\n3. **Multi-Relational Graph Transformer for Automatic Short Answer Grading**. *Rajat Agarwal, Varun Khurana, Karish Grover, Mukesh Mohania and Vikram Goyal*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.146.pdf)]\n4. **Event Schema Induction with Double Graph Autoencoders**. *Xiaomeng Jin, Manling Li and Heng Ji*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.147.pdf)]\n5. **Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion**. *Huda Hakami, Mona Hakami, Angrosh Mandya and Danushka Bollegala*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.209.pdf)]\n6. **FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations**. *Leonardo Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer and Mohit Bansal*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.236.pdf)]\n7. **Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering**. *Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu and Yong Zhu*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.286.pdf)]\n8. **Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization**. *Jingyi You, Dongyuan Li, Hidetaka Kamigaito, Kotaro Funakoshi and Manabu Okumura*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.301.pdf)]\n9. **SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis**. *Zheng Zhang, Zili Zhou and Yanna Wang*. ***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.362.pdf)]\n\n\n***COLING 2022***\n1. **TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph**. *Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He and Yuexian Hou*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.62.pdf)]\n2. **Hierarchical Information Matters: Text Classification via Tree Based Graph Neural Network**. *Chong Zhang, He Zhu, Xingyu Peng, Junran Wu and Ke Xu*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.79.pdf)]\n3. **ConTextING: Granting Document-Wise Contextual Embeddings to Graph Neural Networks for Inductive Text Classification**. *Yen-Hao Huang, Yi-Hsin Chen and Yi-Shin Chen*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.100.pdf)]\n5. **Dynamic Relevance Graph Network for Knowledge-Aware Question Answering**. *Chen Zheng and Parisa Kordjamshidi*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.116.pdf)]\n8. **Semantic Structure Based Query Graph Prediction for Question Answering over Knowledge Graph**. *Mingchen Li and Shihao Ji*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.135.pdf)]\n11. **Event Detection with Dual Relational Graph Attention Networks**. *Jiaxin Mi, Po Hu and Peng Li*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.172.pdf)]\n13. **ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification**. *Meiqi Chen, Yixin Cao, Kunquan Deng, Mukai Li, Kun Wang, Jing Shao and Yan Zhang*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.185.pdf)]\n18. **Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis**. *Siwen Luo, Yihao Ding, Siqu Long, Josiah Poon and Soyeon Caren Han*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.256.pdf)]\n23. **Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations**. *Wessel Poelman, Rik van Noord and Johan Bos*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.367.pdf)]\n24. **GraDA: Graph Generative Data Augmentation for Commonsense Reasoning**. *Adyasha Maharana and Mohit Bansal*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.397.pdf)]\n26. **Topology Imbalance and Relation Inauthenticity Aware Hierarchical Graph Attention Networks for Fake News Detection**. *Li Gao, Lingyun Song, Jie Liu, Bolin Chen and Xuequn Shang*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.415.pdf)]\n29. **Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation**. *Binh Nguyen, Long Nguyen and Dien Dinh*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.444.pdf)]\n31. **Multi Graph Neural Network for Extractive Long Document Summarization**. *Xuan-Dung Doan, Le-Minh Nguyen and Khac-Hoai Nam Bui*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.512.pdf)]\n32. **A Survey of Automatic Text Summarization Using Graph Neural Networks**. *Marco Ferdinand Salchner and Adam Jatowt*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.536.pdf)]\n33. **HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization**. *Tuan-Anh Phan, Ngoc-Dung Ngoc Nguyen and Khac-Hoai Nam Bui*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.545.pdf)]\n34. **GRETEL: Graph Contrastive Topic Enhanced Language Model for Long Document Extractive Summarization**. *Qianqian Xie, Jimin Huang, Tulika Saha and Sophia Ananiadou*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.546.pdf)]\n35. **Social Bot-Aware Graph Neural Network for Early Rumor Detection**. *Zhen Huang, Zhilong Lv, Xiaoyun Han, Binyang Li, Menglong Lu and Dongsheng Li*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.580.pdf)]\n36. **Composition-based Heterogeneous Graph Multi-channel Attention Network for Multi-aspect Multi-sentiment Classification**. *Hao Niu, Yun Xiong, Jian Gao, Zhongchen Miao, Xiaosu Wang, Hongrun Ren, Yao Zhang and Yangyong Zhu*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.594.pdf)]\n37. **Learnable Dependency-based Double Graph Structure for Aspect-based Sentiment Analysis**. *Yinglong Ma and Yunhe Pang*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.618.pdf)]\n38. **Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis**. *Zijie Lin, Bin Liang, Yunfei Long, Yixue Dang, Min Yang, Min Zhang and Ruifeng Xu*. ***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.622.pdf)]\n\n\n## Comprehensive GNN Paperlist\n\n[thunlp\u002FGNNPapers](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers)\n\n[naganandy\u002Fgraph-based-deep-learning-literature](https:\u002F\u002Fgithub.com\u002Fnaganandy\u002Fgraph-based-deep-learning-literature)\n\n[nnzhan\u002FAwesome-Graph-Neural-Networks](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FAwesome-Graph-Neural-Networks)\n\n## Tutorials\n\n[EMNLP 2019 GNNs-for-NLP](https:\u002F\u002Fgithub.com\u002Fsvjan5\u002FGNNs-for-NLP)\n\n[CS224W: Machine Learning with Graphs](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224w\u002Findex.html#content)\n\n## Tools\n\n[Deep Graph Library (DGL)](https:\u002F\u002Fgithub.com\u002Fdmlc\u002Fdgl)\n\n[PyTorch Geometric (PyG)](https:\u002F\u002Fgithub.com\u002Frusty1s\u002Fpytorch_geometric)\n\n## Thesis\n\n[Natural Language Processing and Text Mining with Graph-Structured Representations](https:\u002F\u002Fsites.ualberta.ca\u002F~bang3\u002Ffiles\u002FPhD-Thesis.pdf), Bang Liu, University of Alberta.\n\n[Deep learning with graph-structured representations](https:\u002F\u002Fpure.uva.nl\u002Fws\u002Ffiles\u002F46900201\u002FThesis.pdf), Thomas Norbert Kipf, University of Amsterdam.\n\n[Neural Graph Embedding Methods for Natural Language Processing](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.03042), Shikhar Vashishth, Indian Institute of Science.\n\n[The resurgence of structure in deep neural networks](https:\u002F\u002Fwww.repository.cam.ac.uk\u002Fhandle\u002F1810\u002F292230), Petar Veliˇckovi´c, University of Cambridge.\n\n\n\n\n","# GNN4NLP-论文\n![](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=最新提交&message=2022\u002F09\u002F20&color=important) ![](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=最新&message=COLING-2022&color=red)\n\n这是一份关于图神经网络方法在自然语言处理领域应用的近期论文列表。目前，该仓库收录了在ACL、EMNLP、NAACL-HLT、COLING、ICLR、WWW、IJCAI、AAAI、NIPS、ICML、KDD、SIGIR等会议上发表的论文。\n\n- **新增！2022年10月12日：新增COLING-2022！**\n\n- 2022年9月20日：新增NAACL-2022\n\n- 2022年5月23日：新增ACL-2022\n\n- 2021年11月9日：新增EMNLP-2021\n\n- 2021年7月28日：新增ACL-2021\n\n- 2021年5月24日：新增NAACL-2021\n\n- 2020年12月14日：新增COLING-2020\n\n- 2020年12月1日：新增EMNLP-2020\n\n- 2020年6月24日：新增ACL-2020、GNN工具及博士论文。\n\n## 分类体系\n\n### 基础NLP任务\n\n1. **利用图卷积网络将句法和语义信息融入词嵌入**。*Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya 和 Partha Talukdar*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.04283)] [[代码](http:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FWordGCN)]\n\n2. **基于词汇表的图神经网络用于中文命名实体识别**。*Tao Gui, Yicheng Zou 和 Qi Zhang*。***EMNLP 2019*** [[pdf](http:\u002F\u002Fqizhang.info\u002Fpaper\u002Femnlp-2019.ner.pdf)]\n\n3. **再探句法：关系图卷积网络用于性别歧义代词消解**。*Yinchuan Xu, Junlin Yang*。***GBNLP@ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW19-3814.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fianycxu\u002FRGCN-with-BERT)]\n\n4. **通过异质语言学图增强中文预训练语言模型**。*Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang, Bowen Yu, Hongsong Zhu 和 Tingwen Liu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.140.pdf)]\n\n5. **在细粒度实体类型标注中，通过可扩展的图推理从兄弟提及中学习**。*Yi Chen, Jiayang Cheng, Haiyun Jiang, Lemao Liu, Haisong Zhang, Shuming Shi 和 Ruifeng Xu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.147.pdf)]\n\n6. **变分图自编码作为廉价监督用于AMR共指消解**。*Irene Li, Linfeng Song, Kun Xu 和 Dong Yu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.199.pdf)]\n\n7. **用于AMR解析与生成的图预训练**。*Xuefeng Bai, Yulong Chen 和 Yue Zhang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.415.pdf)]\n\n8. **使用上下文向量结合图微调改进词嵌入**。*Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia, Yufei Huang, Guojiang Zhao, Yue Zhang 和 Stan Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.561.pdf)]\n\n   \n\n### 文本分类\n\n1. **用于半监督短文本分类的异质图注意力网络**。*Linmei Hu, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li*。***EMNLP 2019*** [[pdf](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F74.pdf)]\n\n2. **通过使用类别词图空间的嵌入来提升意图分类中的域外检测**。*Paulo Cavalin, Victor Henrique Alves Ribeiro, Ana Appel 和 Claudio Pinhanez*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.324.pdf)]\n\n3. **用于文档分类的文本图Transformer**。*Haopeng Zhang 和 Jiawei Zhang*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.668.pdf)]\n\n4. **基于边标签图神经网络原型网络的少样本文本分类**。*Chen Lyu, Weijie Liu 和 Ping Wang*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.485.pdf)]\n\n5. **用于文本分类的归纳主题变分图自编码器**。*Qianqian Xie, Jimin Huang, Pan Du, Min Peng 和 Jian-Yun Nie*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.333.pdf)]\n\n6. **用于多标签文本分类的标签特定双图神经网络**。*Qianwen Ma, Chunyuan Yuan, Wei Zhou 和 Songlin Hu*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.298.pdf)]\n\n7. **基于异质图神经网络的跨语言文本分类**。*Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu 和 Zhisheng Wang*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.78.pdf)]\n\n8. **基于关键词图的弱监督文本分类**。*Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu 和 Shuigeng Zhou*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.222.pdf)]\n\n9. **用于短文本分类的层次化异质图表示学习**。*Yaqing Wang, Song Wang, Quanming Yao 和 Dejing Dou*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.247.pdf)]\n\n10. **用于文本分类的深度注意力扩散图神经网络**。*Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang 和 Xiaoyue Feng*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.642.pdf)]\n\n11. **文本分类中的词袋、图与序列：质疑文本图的必要性以及宽广MLP的惊人实力**。*Lukas Galke 和 Ansgar Scherp*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.279.pdf)]\n\n12. **基于文本蕴含与软传递性的蕴涵图学习**。*Zhibin Chen, Yansong Feng 和 Dongyan Zhao*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.406.pdf)]\n\n\n### 情感分析\n\n1. **基于方面的情感分类：方面特定的图卷积网络**。*Chen Zhang, Qiuchi Li 和 Dawei Song*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03477)] [[代码](https:\u002F\u002Fgithub.com\u002FGeneZC\u002FASGCN)]\n\n2. **利用新颖的标注策略进行结构化情感分析的有效标记图建模**。*Wenxuan Shi, Fei Li, Jingye Li, Hao Fei 和 Donghong Ji*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.291.pdf)]\n\n3. **基于句法感知的方面级情感分类：图注意力网络**。*Binxuan Huang 和 Kathleen M. Carley*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.02606)]\n\n4. **用于方面级情感分析的关系图注意力网络**。*Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12362.pdf)]\n\n5. **面向方面级情感分类的句法感知图注意力网络**。*Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang 和 Houfeng Wang*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.69.pdf)]\n\n6. **基于多个依存树的图集成学习用于方面级情感分类**。*Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He 和 Bowen Zhou*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.229.pdf)]\n\n### 问答\n\n1. **BAG：用于多跳推理问答的双向注意力实体图卷积网络。** *曹宇、方萌和陶大成。* ***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1032.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fcaoyu1991\u002FBAG)]\n\n2. **基于图卷积网络跨文档推理的问答**。*Nicola De Cao、Wilker Aziz 和 Ivan Titov。* ***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1240.pdf)]\n\n3. **大规模多跳阅读理解的认知图**。*丁明、周畅、陈启斌、杨洪霞和唐杰。* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05460)] [[代码](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FCogQA)]\n\n4. **用于多跳推理的动态融合图网络**。*肖云轩、屈燕茹、邱琳、周浩、李磊、张伟楠和于勇。* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.06933)]\n\n5. **通过异构图推理实现跨多文档的多跳阅读理解**。*涂明、王光涛、黄静、汤云、何晓东和周博文。* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07374)]\n\n6. **DialogueGCN：一种用于对话中情感识别的图卷积神经网络**。*Deepanway Ghosal、Navonil Majumder、Soujanya Poria、Niyati Chhaya 和 Alexander Gelbukh。* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11540)]\n\n7. **GEAR：用于事实核查的基于图的证据聚合与推理**。*周杰、韩旭、杨程、刘志远、王立峰、李昌成和孙茂松。* ***ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1085)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGEAR)]\n\n8. **面向事实核查的语义级图推理**。*钟万军、徐晶晶、唐杜宇、许泽南、段楠、周明、王家海和尹健。* ***Arxiv 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03745)]\n\n9. **知识图谱上的复杂问题解答的消息传递**。*Svitlana Vakulenko、Javier David Fernandez Garcia、Axel Polleres、Maarten de Rijke、Michael Cochez。* ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06917?context=cs.CL)]\n\n10. **基于图注意力网络的知识感知文本蕴涵**。*陈道源、李亚亮、杨敏、郑海涛、沈颖。* ***CIKM 2019*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002F10.1145\u002F3357384.3358071)]\n\n11. **基于核图注意力网络的细粒度事实核查**。*刘正浩、熊晨艳、孙茂松、刘志远。* ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09796.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n\n12. **序列到序列的知识图谱补全与问答**。*Apoorv Saxena、Adrian Kochsiek 和 Rainer Gemulla。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.201.pdf)]\n\n13. **KG-FiD：在解码器融合中注入知识图谱以进行开放域问答**。*于东汉、朱成刚、方宇威、于文豪、王硕航、徐一冲、任翔、杨一鸣和曾迈克尔。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.340.pdf)]\n\n14. **AdaLoGN：用于基于推理的机器阅读理解的自适应逻辑图网络**。*李晓、程功、陈子恒、孙亚伟和曲宇中。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.494.pdf)]\n\n   \n\n### 信息抽取\n\n1. **基于知识图嵌入和图卷积网络的长尾关系抽取**。*张宁宇、邓淑敏、孙占林、王冠英、陈曦、张伟和陈华俊。* ***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1306.pdf)]\n\n2. **面向关系抽取的注意力引导图卷积网络**。*郭志江、张燕和陆伟。* ***ACL 2019*** [[pdf](http:\u002F\u002Fwww.statnlp.org\u002Fpaper\u002F2019\u002Fattention-guided-graph-convolutional-networks-relation-extraction.html)] [[代码](https:\u002F\u002Fgithub.com\u002FCartus\u002FAGGCN_TACRED)]\n\n3. **用于关系抽取的参数生成式图神经网络**。*朱浩、林彦凯、刘志远、傅杰、蔡宗盛和孙茂松。* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00756)]\n\n4. **GraphRel：将文本建模为关系图以进行实体和关系联合抽取**。*傅子睿、李鹏轩和马伟云。* ***ACL 2019*** [[pdf](https:\u002F\u002Ftsujuifu.github.io\u002Fprojs\u002Facl19_graph-rel.html)] [[代码](https:\u002F\u002Fgithub.com\u002Ftsujuifu\u002Fpytorch_graph-rel)]\n\n5. **增强型多通道图卷积网络用于方面情感三元组抽取**。*陈浩、翟泽鹏、冯方祥、李瑞凡和王小杰。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.212.pdf)]\n\n   \n\n### 文本生成\n\n1. **基于图变换器从知识图谱生成文本**。*Rik Koncel-Kedziorski、Dhanush Bekal、Yi Luan、Mirella Lapata 和 Hannaneh Hajishirzi。* ***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1238.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Frikdz\u002FGraphWriter)]\n\n2. **基于图到序列模型为中国文章生成连贯评论**。*李伟、徐晶晶、何延成、闫胜利、吴云芳和孙旭。* ***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.01231)] [[代码](https:\u002F\u002Fgithub.com\u002Flancopku\u002FGraph-to-seq-comment-generation)]\n\n3. **利用双重图表示增强 AMR 到文本的生成**。*Leonardo F. R. Ribeiro、Claire Gardent 和 Iryna Gurevych。* ***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.00352)]\n\n4. **用于提取式文档摘要的异构图神经网络**。*王丹青、刘鹏飞、郑怡宁、邱希鹏、黄璇婧。* ***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12393.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fbrxx122\u002FHeterSUMGraph)]\n\n5. **通过预训练语言模型生成解释图：一项基于对比学习的实证研究**。*Swarnadeep Saha、Prateek Yadav 和 Mohit Bansal。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.85.pdf)]\n\n6. **基于图增强的对比学习用于放射学发现摘要**。*胡金鹏、李卓、陈志宏、李振、万翔和张宗辉。* ***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.320.pdf)]\n\n### 对话\n\n1. **用于多领域对话状态跟踪的动态模式图融合网络**。*Yue Feng、Aldo Lipani、Fanghua Ye、Qiang Zhang 和 Emine Yilmaz*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.10.pdf)]\n\n2. **HeterMPC：一种用于多方对话中回复生成的异构图神经网络**。*Jia-Chen Gu、Chao-Hong Tan、Chongyang Tao、Zhen-Hua Ling、Huang Hu、Xiubo Geng 和 Daxin Jiang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.349.pdf)]\n\n3. **全局控制，局部理解：用于情感支持对话的全局到局部层次化图网络**。*Wei Peng、Yue Hu、Luxi Xing、Yuqiang Xie、Yajing Sun、Yunpeng Li*。***IJCAI 2022*** [[pdf](http:\u002F\u002Farxiv.org\u002Fabs\u002F2204.12749)]\n   \n\n### 知识图谱\n\n1. **利用图神经网络估计知识图谱中的节点重要性**。*Namyong Park、Andrey Kan、Xin Luna Dong、Tong Zhao 和 Christos Faloutsos*。***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Festimating-node-importance-in-knowledge-graphs-using-graph-neural-networks)]\n\n2. **用于节点分类的哈希图卷积**。*Wenting Zhao、Zhen Cui、Chunyan Xu、Chengzheng Li、Tong Zhang、Jian Yang*。***CIKM 2019*** [[pdf](https:\u002F\u002Feasychair.org\u002Fpublications\u002Fpreprint\u002FlhT3)]\n\n3. **基于自监督自适应图对齐的多语言知识图谱补全**。*Zijie Huang、Zheng Li、Haoming Jiang、Tianyu Cao、Hanqing Lu、Bing Yin、Karthik Subbian、Yizhou Sun 和 Wei Wang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.36.pdf)]\n\n4. **知识图谱嵌入的高效超参数搜索**。*Yongqi Zhang、Zhanke Zhou、Quanming Yao 和 Yong Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.194.pdf)]\n\n5. **CAKE：一个可扩展的常识感知框架，用于多视角知识图谱补全**。*Guanglin Niu、Bo Li、Yongfei Zhang 和 Shiliang Pu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.205.pdf)]\n\n6. **SimKGC：使用预训练语言模型的简单对比式知识图谱补全**。*Liang Wang、Wei Zhao、Zhuoyu Wei 和 Jingming Liu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.295.pdf)]\n\n7. **RotateQVS：将时间信息表示为四元数向量空间中的旋转，用于时间知识图谱补全**。*Kai Chen、Ye Wang、Yitong Li 和 Aiping Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.402.pdf)]\n\n8. **用于时间知识图谱推理的复杂演化模式学习**。*Zixuan Li、Saiping Guan、Xiaolong Jin、Weihua Peng、Yajuan Lyu、Yong Zhu、Long Bai、Wei Li、Jiafeng Guo 和 Xueqi Cheng*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-short.32.pdf)]\n    \n\n### 异常文本检测\n\n1. **利用图卷积网络进行辱骂性语言检测**。*Pushkar Mishra、Marco Del Tredici、Helen Yannakoudakis 和 Ekaterina Shutova*。***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1221.pdf)]\n\n2. **利用图卷积网络编码社交信息，用于新闻媒体中的政治观点检测**。*Chang Li 和 Dan Goldwasser*。***ACL 2019*** [[pdf](https:\u002F\u002Fwww.cs.purdue.edu\u002Fhomes\u002Fdgoldwas\u002F\u002Fdownloads\u002Fpapers\u002FLiG_acl_2019.pdf)]\n\n3. **利用图卷积网络进行垃圾评论检测**。*Ao Li、Zhou Qin、Runshi Liu、Yiqun Yang、Dong Li*。***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10679v1)]\n\n4. **三思而后行：利用审慎的上下文扩展，在知识图谱上进行对话式问答**。*Philipp Christmann、Rishiraj Saha Roy、Abdalghani Abujabal、Jyotsna Singh、Gerhard Weikum*。***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03262v1)]\n\n5. **GCAN：面向可解释的社交媒体假新闻检测的图感知协同注意力网络**。*Yi-Ju Lu、Cheng-Te Li*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.11648.pdf)]\n\n6. **通过持续改进社交上下文表示，利用图神经网络应对假新闻检测挑战**。*Nikhil Mehta、Maria Pacheco 和 Dan Goldwasser*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.97.pdf)]\n\n    \n\n### 视觉问答\n\n1. **面向视觉问答的关系感知图注意力网络**。*Linjie Li、Zhe Gan、Yu Cheng 和 Jingjing Liu*。***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.12314)]\n\n2. **用于关系推理的语言条件图网络**。*Ronghang Hu、Anna Rohrbach、Trevor Darrell 和 Kate Saenko*。***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.04405)] [[代码](http:\u002F\u002Fronghanghu.com\u002Flcgn)]\n\n3. **基于多模态上下文图理解和自监督开放集理解的教科书式问答**。*Daesik Kim、Seonhoon Kim 和 Nojun Kwak*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.00232)]\n\n4. **面向视觉问答的对齐双通道图卷积网络**。*Qingbao Huang、Jielong Wei、Yi Cai、Changmeng Zheng、Junying Chen、Ho-fung Leung、Qing Li*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.642.pdf)] \n\n5. **用于视觉问答的多模态神经图记忆网络**。*Mahmoud Khademi*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.643.pdf)] \n\n6. **建模时空实体图，用于程序化多模态机器理解**。*Huibin Zhang、Zhengkun Zhang、Yao Zhang、Jun Wang、Yufan Li、Ning Jiang、Xin Wei 和 Zhenglu Yang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.84.pdf)]\n\n7. **通过跨模态图卷积网络进行多模态讽刺检测**。*Bin Liang、Chenwei Lou、Xiang Li、Min Yang、Lin Gui、Yulan He、Wenjie Pei 和 Ruifeng Xu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.124.pdf)]\n\n    \n\n### 理论\n\n1. **HetGNN：异构图神经网络**。*Chuxu Zhang、Dongjin Song、Chao Huang、Ananthram Swami 和 Nitesh V. Chawla*。***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Fhetgnn-heterogeneous-graph-neural-network)]\n\n2. **GMNN：图马尔可夫神经网络**。*Meng Qu、Yoshua Bengio 和 Jian Tang*。***ICML 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.06214.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FGMNN)]\n\n3. **无监督依存关系图网络**。*Yikang Shen、Shawn Tan、Alessandro Sordoni、Peng Li、Jie Zhou 和 Aaron Courville*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.327.pdf)]\n\n\n\n## 按会议划分\n\n***NAACL-HLT 2019***\n\n1. **BAG：用于多跳推理问答的双向注意力实体图卷积网络。** *曹宇、方萌和陶大成。* ***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1032.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fcaoyu1991\u002FBAG)]\n2. **基于图卷积网络的辱骂语言检测**。 *普什卡尔·米什拉、马可·德尔·特雷迪奇、海伦·扬纳库达基斯和叶卡捷琳娜·舒托娃*。***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1221.pdf)]\n3. **基于图变换器的知识图谱文本生成**。 *里克·孔切尔-凯济奥尔斯基、达努什·贝卡尔、伊恩·卢安、米雷拉·拉帕塔和汉纳内·哈吉希尔齐*。***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1238.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Frikdz\u002FGraphWriter)]\n4. **利用图卷积网络跨文档推理的问答系统**。 *尼古拉·德·考、威尔克·阿齐兹和伊万·蒂托夫*。***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1240.pdf)]\n5. **通过知识图谱嵌入与图卷积网络进行长尾关系抽取**。 *张宁宇、邓淑敏、孙占林、王冠英、陈曦、张伟和陈华军*。***NAACL-HLT 2019***。[[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FN19-1306.pdf)]\n\n   \n\n***KDD 2019***\n\n1. **利用图神经网络估计知识图谱中的节点重要性**。 *朴南勇、安德烈·坎、辛露娜·董、赵彤和克里斯托斯·法卢索斯*。***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Festimating-node-importance-in-knowledge-graphs-using-graph-neural-networks)]\n2. **HetGNN：异构图神经网络**。 *张楚旭、宋东进、黄超、阿南特拉姆·斯瓦米和尼特什·V·查乌拉*。***KDD 2019*** [[pdf](https:\u002F\u002Fwww.kdd.org\u002Fkdd2019\u002Faccepted-papers\u002Fview\u002Fhetgnn-heterogeneous-graph-neural-network)]\n\n   \n\n***ICML 2019***\n\n1. **GMNN：图马尔可夫神经网络**。 *曲萌、约书亚·本吉奥和唐建*。***ICML 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.06214.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FDeepGraphLearning\u002FGMNN)]\n\n   \n\n***ICCV 2019***\n\n1. **面向视觉问答的关系感知图注意力网络**。 *李林杰、甘哲、程宇和刘静静*。***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.12314)]\n2. **用于关系推理的语言条件图网络**。 *胡荣航、安娜·罗尔巴赫、特雷弗·达雷尔和凯特·萨恩科*。***ICCV 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.04405)] [[代码](http:\u002F\u002Fronghanghu.com\u002Flcgn)]\n\n\n\n***ACL 2019***\n\n1. **用于关系抽取的注意力引导图卷积网络**。 *郭志江、张燕和陆伟*。***ACL 2019*** [[pdf](http:\u002F\u002Fwww.statnlp.org\u002Fpaper\u002F2019\u002Fattention-guided-graph-convolutional-networks-relation-extraction.html)] [[代码](https:\u002F\u002Fgithub.com\u002FCartus\u002FAGGCN_TACRED)]\n2. **GEAR：用于事实核查的基于图的证据聚合与推理**。 *周杰、韩旭、杨成、刘志远、王立峰、李昌成和孙茂松*。***ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FP19-1085)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGEAR)]\n3. **用于大规模多跳阅读理解的认知图**。 *丁明、周畅、陈启斌、杨红霞和唐洁*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05460)] [[代码](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FCogQA)]\n4. **基于图到序列模型的中文文章连贯评论生成**。 *李伟、徐晶晶、何延成、闫胜利、吴云芳和孙旭*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.01231)] [[代码](https:\u002F\u002Fgithub.com\u002Flancopku\u002FGraph-to-seq-comment-generation)]\n5. **用于多跳推理的动态融合图网络**。 *肖云轩、屈艳茹、邱琳、周浩、李磊、张伟楠和于勇*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.06933)]\n6. **利用图卷积网络编码社交信息以检测新闻媒体中的政治立场**。 *李畅和丹·戈德瓦瑟*。***ACL 2019*** [[pdf](https:\u002F\u002Fwww.cs.purdue.edu\u002Fhomes\u002Fdgoldwas\u002F\u002Fdownloads\u002Fpapers\u002FLiG_acl_2019.pdf)]\n7. **用于关系抽取的参数生成式图神经网络**。 *朱浩、林彦凯、刘志远、傅杰、蔡宗胜和孙茂松*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00756)]\n8. **利用图卷积网络在词嵌入中融入句法和语义信息**。 *希卡尔·瓦西斯特、马尼克·班达里、普拉蒂克·亚达夫、皮尤什·赖、奇兰吉布·巴塔查里亚和帕尔塔·塔卢克达尔*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.04283)] [[代码](http:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FWordGCN)]\n9. **GraphRel：将文本建模为关系图以进行实体与关系联合抽取**。 *傅子睿、李鹏轩和马伟云*。***ACL 2019*** [[pdf](https:\u002F\u002Ftsujuifu.github.io\u002Fprojs\u002Facl19_graph-rel.html)] [[代码](https:\u002F\u002Fgithub.com\u002Ftsujuifu\u002Fpytorch_graph-rel)]\n10. **通过异构图推理实现跨多篇文档的多跳阅读理解**。 *涂明、王广涛、黄静、汤云、何晓东和周博文*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.07374)]\n11. **结合多模态上下文图理解和自监督开放集理解的教科书问答**。 *金大植、金善勋和郭诺俊*。***ACL 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.00232)]\n12. **再看句法：用于性别模糊代词消解的关系图卷积网络**。 *许银川、杨俊林*。***GBNLP@ACL 2019*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002FW19-3814.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fianycxu\u002FRGCN-with-BERT)]\n\n\n\n***EMNLP-IJCNLP 2019***\n\n1. **基于词典的图神经网络用于中文命名实体识别**。 *桂涛、邹一诚和张琪*。***EMNLP 2019*** [[pdf](http:\u002F\u002Fqizhang.info\u002Fpaper\u002Femnlp-2019.ner.pdf)]\n2. **基于方面特定图卷积网络的方面级情感分类**。 *张晨、李秋池和宋大伟*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.03477)]\n3. **DialogueGCN：用于对话中情绪识别的图卷积神经网络**。 *迪潘韦·戈萨尔、纳沃尼尔·马久姆达尔、苏贾尼亚·波里亚、尼娅蒂·查亚和亚历山大·盖尔布赫*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11540)]\n4. **利用双重图表示增强AMR到文本的生成**。 *莱昂纳多·F·R·里贝罗、克莱尔·加登和伊琳娜·古列维奇*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.00352)]\n5. **用于半监督短文本分类的异构图注意力网络**。 *胡琳梅、杨天驰、石川、姬厚业和李晓丽*。***EMNLP 2019*** [[pdf](http:\u002F\u002Fshichuan.org\u002Fdoc\u002F74.pdf)]\n6. **基于图注意力网络的句法感知方面级情感分类**。 *黄彬轩和凯瑟琳·M·卡利*。***EMNLP 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.02606)]\n\n\n\n***CIKM 2019***\n\n1. **基于图卷积网络的垃圾评论检测**。*Ao Li、Zhou Qin、Runshi Liu、Yiqun Yang、Dong Li.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.10679v1)]\n2. **Fi-GNN：通过图神经网络建模特征交互以进行点击率预测**。*Zekun Li、Zeyu Cui、Shu Wu、Xiaoyu Zhang、Liang Wang.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05552)] [[代码](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FFi_GNNs)]\n3. **知识图谱上的复杂问题回答中的消息传递**。*Svitlana Vakulenko、Javier David Fernandez Garcia、Axel Polleres、Maarten de Rijke、Michael Cochez.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06917?context=cs.CL)]\n4. **基于图注意力网络的知识感知文本蕴涵推理**。*Daoyuan Chen、Yaliang Li、Min Yang、Hai-Tao Zheng、Ying Shen.*  ***CIKM 2019*** [[pdf]()]\n5. **先看后跳：利用审慎的上下文扩展实现知识图谱上的对话式问答**。*Philipp Christmann、Rishiraj Saha Roy、Abdalghani Abujabal、Jyotsna Singh、Gerhard Weikum.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.03262v1)]\n6. **基于可追溯异构图表示学习的跨领域方面类别迁移与检测**。*Zhuoren Jiang、Jian Wang、Lujun Zhao、Changlong Sun、Yao Lu、Xiaozhong Liu.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.11610)]\n7. **面向用户主动社交电商推荐的关系感知图卷积网络**。*Fengli Xu、Jianxun Lian、Zhenyu Han、Yong Li、Yujian Xu、Xing Xie.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fuploads\u002Fprod\u002F2019\u002F09\u002FCIKM19-recogcn.pdf)]\n8. **用于节点分类的哈希图卷积**。*Wenting Zhao、Zhen Cui、Chunyan Xu、Chengzheng Li、Tong Zhang、Jian Yang.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Feasychair.org\u002Fpublications\u002Fpreprint\u002FlhT3)]\n9. **受引力启发的有向链接预测图自动编码器**。*Guillaume Salha、Stratis Limnios、Romain Hennequin、Viet Anh Tran、Michalis Vazirgiannis.*  ***CIKM 2019*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09570)]\n10. **基于图卷积网络的多源谣言检测**。*Ming Dong、Bolong Zheng、Nguyen Quoc Viet Hung、Han Su、Guohui Li.*  ***CIKM 2019*** [[pdf]()]\n\n\n\n***ICLR 2020***\n\n1. **基于记忆的图网络**。*Amir hosein Khasahmadi、Kaveh Hassani、Parsa Moradi、Leo Lee、Quaid Morris*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fpdf?id=r1laNeBYPB)]\n2. **InfoGraph：通过互信息最大化实现无监督和半监督的图级别表示学习**。*Fan-Yun Sun、Jordan Hoffman、Vikas Verma、Jian Tang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1lfF2NYvH&noteId=r1lfF2NYvH)]\n3. **图神经网络的逻辑表达能力**。*Pablo Barceló、Egor V. Kostylev、Mikael Monet、Jorge Pérez、Juan Reutter、Juan Pablo Silva*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=r1lZ7AEKvB&noteId=r1lZ7AEKvB)]\n4. **结构化世界模型的对比学习**。*Thomas Kipf、Elise van der Pol、Max Welling*. ***ICLR 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.12247)] [[代码](https:\u002F\u002Fgithub.com\u002Ftkipf\u002Fc-swm)]\n5. **Geom-GCN：几何图卷积网络**。*Hongbin Pei、Bingzhe Wei、Kevin Chen-Chuan Chang、Yu Lei、Bo Yang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=S1e2agrFvS)]\n6. **图神经网络预训练策略**。*Weihua Hu、Bowen Liu、Joseph Gomes、Marinka Zitnik、Percy Liang、Vijay Pande、Jure Leskovec*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=HJlWWJSFDH)]\n7. **用于大规模知识图谱推理的动态剪枝消息传递网络**。*Xiaoran Xu、Wei Feng、Yunsheng Jiang、Xiaohui Xie、Zhiqing Sun、Zhi-Hong Deng*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=rkeuAhVKvB)]\n8. **图神经网络学不到什么：深度与宽度的权衡**。*Andreas Loukas*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=B1l2bp4YwS)]\n9. **LambdaNet：利用图神经网络进行概率类型推断**。*Jiayi Wei、Maruth Goyal、Greg Durrett、Isil Dillig*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=Hkx6hANtwH)]\n10. **图卷积强化学习**。*Jiechuan Jiang、Chen Dun、Tiejun Huang、Zongqing Lu*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=HkxdQkSYDB)]\n11. **DropEdge：迈向节点分类的深层图卷积网络**。*Yu Rong、Wenbing Huang、Tingyang Xu、Junzhou Huang*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=Hkx1qkrKPr)]\n12. **利用图神经网络进行高效的概率逻辑推理**。*Yuyu Zhang、Xinshi Chen、Yuan Yang、Arun Ramamurthy、Bo Li、Yuan Qi、Le Song*. ***ICLR 2020*** [[pdf](https:\u002F\u002Fopenreview.net\u002Fforum?id=rJg76kStwH)]\n\n\n\n***WWW 2020***\n\n1. **TaxoExpan：基于位置增强图神经网络的自监督分类体系扩展**。*Jiaming Shen、Zhihong Shen、Chenyan Xiong、Chi Wang、Kuansan Wang、Jiawei Han*. ***WWW 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.09522)]\n2. **知识图谱之间的集体多类型实体对齐**。*Qi Zhu、Hao Wei、Bunyamin Sisman、Da Zheng、Christos Faloutsos、Xin Luna Dong 和 Jiawei Han*. ***WWW 2020*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380289)]\n3. **基于自由文本知识图谱的复杂事实型问题回答**。*Chen Zhao、Chenyan Xiong、Xin Qian 和 Jordan Boyd-Graber*. ***WWW 2020*** [[pdf](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3366423.3380197)]\n\n\n\n***ACL 2020***\n\n1. **基于核图注意力网络的细粒度事实核查**。*刘正浩、熊晨燕、孙茂松、刘知远*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09796.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n2. **GCAN：面向社交媒体上可解释假新闻检测的图感知协同注意力网络**。*陆怡儒、李承特*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.11648.pdf)]\n3. **用于抽取式文档摘要的异构图神经网络**。*王丹青、刘鹏飞、郑一宁、邱锡鹏、黄轩静*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12393.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fbrxx122\u002FHeterSUMGraph)]\n4. **用于方面级情感分析的关系图注意力网络**。*王凯、沈伟周、杨云毅、全晓俊、王睿*。***ACL 2020*** [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2004.12362.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fshenwzh3\u002FRGAT-ABSA)]\n5. **每篇文档都有其结构：基于图神经网络的归纳式文本分类**。*张宇峰∗、于雪莉∗、崔泽宇、吴舒、温仲振和王亮*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.31.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FTextING)]\n6. **结合语义与结构信息的图卷积网络在争议检测中的应用**。*钟磊、曹娟、盛强、郭俊波、王子昂*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.49.pdf)] [[代码](http:\u002F\u002Fmcg.ict.ac.cn\u002Fcontroversy-detection-dataset.html)]\n7. **线图增强的AMR到文本生成：基于混合阶图注意力网络**。*赵彦斌、陈璐、陈志、曹瑞生、朱苏、于凯*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.67.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fybz79\u002FAMR2text)]\n8. **从知识库中回答多跳复杂问题的查询图生成**。*兰云石、蒋晶*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.91.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Flanyunshi\u002FMulti-hopComplexKBQA)]\n9. **用于生成深度问题的语义图**。*潘良明、谢宇曦、冯岩松、蔡德成、简敏言*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.135.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FWING-NUS\u002FSG-Deep-Question-Generation)]\n10. **基于对话图的策略学习用于开放域对话生成**。*徐军、王海峰、牛政宇、吴华、车万祥、刘婷*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.166.pdf)]\n11. **基于常识知识图谱引导遍历的接地式对话生成**。*张厚宇、刘正浩、熊晨燕、刘知远*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.184.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FConceptFlow)]\n12. **一种新颖的基于图的多模态融合编码器用于神经机器翻译**。*尹永靖、孟凡东、苏金松、周楚伦、杨正元、周杰、罗杰波*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.273.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FDeepLearnXMU\u002FGMNMT)]\n13. **依存句法感知的意见角色标注：基于依存图卷积网络**。*张博、张悦、王睿、李正华、张敏*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.297.pdf)]\n14. **基于图的粗精结合无监督双语词典构建方法**。*任硕、刘淑洁、周明、马帅*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.318.pdf)]\n15. **无监督偏好解耦的图神经网络新闻推荐**。*胡琳梅、许思勇、李晨、杨成、史川、段楠、谢星、周明*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.392.pdf)]\n16. **语义驱动完形填空奖励机制下的知识图谱增强型摘要生成**。*黄路阳、吴凌飞和王璐*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.457.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fluyang-huang96\u002FGraphAugmentedSum)]\n17. **实体感知的基于依存关系的深度图注意力网络用于比较偏好分类**。*马念祖、马祖姆德尔、王浩、刘兵*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.512.pdf)]\n18. **LogicalFactChecker：利用逻辑运算进行事实核查的图模块网络**。*钟万军、唐杜宇、冯章印、段楠、周明、龚明、寿林俊、姜大新、王家海和殷健*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.539.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FKernelGAT)]\n19. **基于语义层级图的事实核查推理**。*钟万军、徐晶晶、唐杜宇、徐泽南、段楠、周明、王家海和殷健*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.549.pdf)]\n20. **基于图注意力网络的文档建模用于多粒度机器阅读理解**。*郑博、文浩洋、梁耀波、段楠、车万祥、姜大新、周明和刘婷*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.599.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FDancingSoul\u002FNQ_BERT-DM)]\n21. **用于图到序列学习的异构图Transformer**。*姚绍伟、王天明、万晓俊*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.640.pdf)] [[代码](https:\u002F\u002Fgithub.com\u002FQAQ-v\u002FHetGT)]\n22. **对齐双通道图卷积网络用于视觉问答**。*黄庆宝、魏杰龙、蔡毅、郑昌猛、陈俊英、梁浩丰、李青*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.642.pdf)]\n23. **用于视觉问答的多模态神经图记忆网络**。*马哈茂德·卡德米*。***ACL 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.acl-main.643.pdf)]\n\n\n***EMNLP 2020***\n\n1. **连接各点：基于路径语言建模的事件图模式归纳**。*李曼玲、曾琪、林莹、曹庆贤、季恒、乔纳森·梅、内森尼尔·钱伯斯和克莱尔·沃斯*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.50.pdf)]\n2. **基于常识知识图谱的多跳推理语言生成**。*季浩哲、柯培、黄绍涵、魏福瑞、朱晓燕和黄民列*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.54.pdf)]\n3. **利用指称图学习图像与文本的表示**。*张博文、胡赫翔、贾因·维汉、伊耶·尤金和沙飞*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.60.pdf)]\n4. **ENT-DESC：通过探索知识图谱生成实体描述**。*程丽英、吴德坤、丙立东、张岩、解占明、陆伟和罗思*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.90.pdf)]\n5. **基于双图的文档级关系抽取推理**。*曾爽、徐润欣、常宝宝和李磊*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.127.pdf)]\n6. **基于实体对嵌入的知识图谱对齐**。*王志春、杨金健和叶小菊*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.130.pdf)]\n7. **面向少样本知识图谱补全的自适应注意力网络**。*盛嘉伟、郭书、陈振宇、岳居伟、王丽红、刘婷雯和徐洪波*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.131.pdf)]\n8. **GraphDialog：将图结构知识融入端到端任务导向对话系统**。*杨世泉、张睿和萨拉·埃尔法尼*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.147.pdf)]\n9. **用于AMR到文本生成的轻量级动态图卷积网络**。*张岩、郭志江、滕志阳、陆伟、科恩·S·B、刘作柱和丙立东*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.169.pdf)]\n10. **通过跨异构语言的元图学习实现跨语言迁移**。*李政、库马尔·穆库尔、威廉·希登、尹冰、魏颖、张宇和杨强*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.179.pdf)]\n11. **基于解耦的持续图表示学习**。*寇晓宇、林彦凯、刘绍博、李鹏、周杰和张岩*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.237.pdf)]\n12. **通过BERT数据增强与约束型Tucker分解进行知识图谱补全，学习物理常识**。*赵振杰、帕帕莱克萨基斯·埃万格洛斯和马晓娟*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.266.pdf)]\n13. **AttnIO：基于内外注意力流的知识图谱探索，用于知识驱动的对话系统**。*郑在勋、孙宝京和吕成源*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.280.pdf)]\n14. **基于层次化注意力异质图网络的神经提取式摘要生成**。*贾瑞鹏、曹亚楠、唐恒竹、方芳、曹聪和王石*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.295.pdf)]\n15. **结合文档关系图的神经主题建模**。*周德宇、胡雪萌和王锐*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.310.pdf)]\n16. **面向句法感知的语义角色标注：基于成分树的图卷积方法**。*马尔切加尼·迭戈和伊万·蒂托夫*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.322.pdf)]\n17. **利用类别词图空间的嵌入改进意图分类中的域外检测**。*卡瓦林·保罗、里贝罗·维克托·恩里克·阿尔维斯、阿佩尔·安娜和皮尼亚内斯·克劳迪奥*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.324.pdf)]\n18. **保持惊人地简单：一种简单的低阶图基解析模型，用于梵语的联合形态句法解析**。*克里希纳·阿姆里特、古普塔·阿希姆、加拉桑吉·迪帕克、萨图鲁里·帕万库马尔和戈亚尔·帕万*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.388.pdf)]\n19. **事件检测：针对图卷积神经网络的门多样性与句法重要性评分**。*赖越达克、阮俊和阮天友*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.435.pdf)]\n20. **稀疏知识图谱上的多跳推理：动态预测与补全**。*吕鑫、韩旭、侯雷、李涓子、刘志远、张伟、张一驰、孔浩和吴苏慧*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.459.pdf)]\n21. **基于双曲知识图谱嵌入的知识关联**。*孙泽群、陈慕豪、胡伟、王承明、戴坚和张伟*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.460.pdf)]\n22. **TeMP：用于时间知识图谱补全的时间消息传递**。*吴家鹏、曹猛、张志杰和哈密顿·W·L*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.462.pdf)]\n23. **利用注意力图卷积网络进行组合范畴语法的超标记**。*田元和、宋燕和夏飞*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.487.pdf)]\n24. **面向文本中数值推理的问题导向图注意力网络**。*陈昆龙、许伟迪、程星毅、邹晓川、张雨雨、宋乐、王泰峰、齐源和楚伟*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.549.pdf)]\n25. **IGSQL：基于数据库模式交互图的上下文依赖文本到SQL生成神经模型**。*蔡逸涛和万晓军*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.560.pdf)]\n26. **多跳问答是否需要图结构？**。*邵楠、崔一鸣、刘婷、王世锦和胡国平*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.583.pdf)]\n27. **DyERNIE：用于时间知识图谱补全的黎曼流形嵌入动态演化**。*韩震、陈鹏、马云普和特雷斯普·沃尔克*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.593.pdf)]\n28. **利用无监督图学习将词语嵌入非向量空间**。*拉比宁·马克西姆、波波夫·谢尔盖、普罗霍伦科娃·柳德米拉和沃伊塔·叶莲娜*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.594.pdf)]\n29. **知识图谱嵌入的去偏处理**。*约瑟夫·费舍尔、阿皮特·米塔尔、帕尔弗雷·戴夫和克里斯托斯·克里斯托杜洛普洛斯*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.595.pdf)]\n30. **面向对话情感识别的关系感知图注意力网络：结合关系位置编码**。*石渡太一、安田由纪、宫崎太郎和后藤淳*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.597.pdf)]\n31. **通过言语化与图注意力网络增强的事实核查程序**。*杨晓宇、聂峰、冯玉飞、刘权、陈志刚和朱晓丹*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.628.pdf)]\n32. **VolTAGE：基于文本音频融合与图卷积网络的收益电话会议波动率预测**。*萨韦尼·拉米特、坎纳·皮尤什、阿加瓦尔·阿尔希娅、贾因·塔鲁、马图尔·普尼特和沙赫·拉吉夫·拉特*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.643.pdf)]\n33. **评估知识图谱嵌入的校准度以实现可信的链接预测**。*萨法维·塔拉、库特拉·达奈和梅伊·埃德加*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.667.pdf)]\n34. **用于文档分类的文本图变换器**。*张浩鹏和张佳伟*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.668.pdf)]\n35. **CoDEx：一个全面的知识图谱补全基准测试集**。*萨法维·塔拉和库特拉·达奈*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.669.pdf)]\n36. **基于规则指导的学习协作智能体用于知识图谱推理**。*雷德仁、蒋刚荣、顾晓涛、孙可轩、毛宇宁和任翔*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.688.pdf)]\n37. **用于多跳问答的层次化图网络**。*方宇威、孙思琪、甘哲、皮莱·罗希特、王硕航和刘静静*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.710.pdf)]\n38. **SRLGRN：语义角色标注图推理网络**。*郑晨和科尔德贾姆希迪·帕丽莎*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-main.714.pdf)]\n39. **LibKGE——用于可复现研究的知识图谱嵌入库**。*布罗斯海特·塞缪尔、鲁菲内利·丹尼尔、科赫西克·艾德里安、贝茨·帕特里克和格穆拉·赖纳*。***EMNLP 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.emnlp-demos.22.pdf)]\n\n***COLING 2020***\n\n1. **用于网络问答的半结构化数据图表示**。*张星耀、寿林俊、裴健、龚明、文利杰和蒋大新*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.5.pdf)]\n2. **基于图卷积网络联合学习面向方面与方面间关系的方面情感分析**。*梁斌、尹荣迪、桂琳、杜嘉晨和徐瑞峰*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.13.pdf)]\n3. **基于图卷积网络的端到端情感原因对抽取**。*陈颖、侯文俊、李守山、吴才聪和张晓强*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.17.pdf)]\n4. **利用方向性图卷积网络进行联合方面抽取与情感分析**。*陈贵民、田元鹤和宋燕*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.24.pdf)]\n5. **异构图神经网络用于预测下一步事件**。*郑建明、蔡飞、凌艳翔和陈洪辉*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.29.pdf)]\n6. **结合图结构与主题词改进摘要式对话摘要生成**。*赵璐璐、许伟然和郭军*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.39.pdf)]\n7. **AprilE：带有伪残差连接的注意力机制用于知识图谱嵌入**。*刘宇章、王鹏、李英泰、邵义展和徐中凯*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.44.pdf)]\n8. **基于几何代数的知识图谱嵌入**。*徐成进、莫杰塔巴·纳耶里、陈永裕和延斯·莱曼*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.46.pdf)]\n9. **利用节点内容的多视图图卷积网络及对抗正则化**。*陆秋豪、德席尔瓦、窦德静、阮天友、森普里特维拉吉、莱因瓦尔德和李云瑶*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.47.pdf)]\n10. **RatE：面向关系自适应的翻译嵌入用于知识图谱补全**。*黄浩、龙国栋、沈涛、江静和张承启*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.48.pdf)]\n11. **语法感知的图注意力网络用于方面级情感分类**。*黄连哲、孙欣、李素坚、张林浩和王厚峰*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.69.pdf)]\n12. **基于方面类别的层次化图卷积网络进行情感分析**。*蔡宏杰、涂耀峰、周祥生、俞建飞和夏锐*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.72.pdf)]\n13. **高精度金融知识图谱构建流水线**。*萨拉·埃尔哈马迪、拉克斯·V·S·拉克什马南、雷蒙德·恩格、迈克尔·辛普森、怀宝兴、王哲峰和王兰君*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.84.pdf)]\n14. **R-VGAE：基于关系变分图自动编码器的无监督先决条件链学习**。*李艾琳、法布里、辛普尔·辛格米雷和德拉戈米尔·拉德夫*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.99.pdf)]\n15. **采用空洞卷积与残差学习的知识图谱嵌入**。*任飞亮、李居臣、张慧慧、刘世磊、李博超、明瑞成和白宇佳*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.134.pdf)]\n16. **文档级关系抽取的图增强双注意力网络**。*李博、叶伟、盛中浩、谢睿、奚向宇和张士坤*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.136.pdf)]\n17. **TeRo：基于时间旋转的时间感知知识图谱嵌入**。*徐成进、莫杰塔巴·纳耶里、福阿德·阿尔库里、哈梅德·沙里亚特·亚兹迪和延斯·莱曼*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.139.pdf)]\n18. **基于双层异构图的文档级关系抽取**。*张振宇、于博文、舒小波、刘廷文、唐恒竹、王宇彬和郭力*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.143.pdf)]\n19. **基于知识图谱中正负证据路径的反权重无监督事实核查**。*金智成和崔基善*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.147.pdf)]\n20. **利用预训练语言模型进行知识图谱补全的多任务学习**。*金宝成、洪泰锡、高英中和徐正允*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.153.pdf)]\n21. **视觉对话中基于图推理的视觉-文本对齐**。*姜天玲、季毅、刘春平和邵海林*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.170.pdf)]\n22. **我知道你在问什么：利用AMR进行常识推理的图路径学习**。*林重佑、吴东旭、张允娜、杨基洙和林辉锡*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.222.pdf)]\n23. **基于全局动态图建模长距离节点关系以支持KBQA**。*王旭、赵帅、韩家乐、程博、杨浩、敖建昌和李珍子*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.231.pdf)]\n24. **基于概念图的句子级自动化图生成用于阅读理解**。*林婉萱和卢春贤*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.240.pdf)]\n25. **用于口语理解的句法图卷积网络**。*何克清、雷淑玉、杨雨书、蒋慧星和王中原*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.246.pdf)]\n26. **先总结再聚合：用于会话情感识别的由全局到局部的异构图推理网络**。*盛东明、王东、申莹、郑海涛和刘浩壮*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.367.pdf)]\n27. **将用户历史融入异构图以进行对话行为识别**。*王东、李自然、郑海涛和申莹*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.372.pdf)]\n28. **基于子实体粒度的多任务学习，利用知识图谱增强神经机器翻译**。*赵洋、向路、朱俊楠、张嘉俊、周宇和宗成青*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.397.pdf)]\n29. **基于知识图谱实体预训练的循环神经网络进行半监督URL分割**。*张浩、罗在宰和理查德·斯普劳特*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.411.pdf)]\n30. **面向文档级关系抽取的全局上下文增强图卷积网络**。*周辉伟、徐义斌、姚卫红、刘哲、郎成坤和江海斌*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.461.pdf)]\n31. **利用主题感知图神经网络提升抽取式文本摘要质量**。*崔鹏、胡乐和刘远超*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.468.pdf)]\n32. **基于边标签图神经网络的原型网络实现少样本文本分类**。*吕晨、刘伟杰和王平*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.485.pdf)]\n33. **基于BERT的层次化图掩码进行事实级抽取式摘要生成**。*袁瑞峰、王子力和李文杰*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.493.pdf)]\n34. **用于跨语言实体对齐的上下文对齐增强交叉图注意力网络**。*谢志文、朱润杰、赵昆松、刘金、周广友和黄继基*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.520.pdf)]\n35. **基于多个依存子图的图卷积用于关系抽取**。*安格罗什·曼迪亚、达努什卡·博勒加拉和弗兰斯·科内恩*。***COLING 2020*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2020.coling-main.565.pdf)]\n\n***NAACL 2021***\n\n1. **基于图卷积网络的联合信息抽取中跨任务实例表示交互与标签依赖**。*Minh Van Nguyen、Viet Lai 和 Thien Huu Nguyen*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.3.pdf)]\n2. **面向联合信息抽取的抽象语义表示引导的图编码与解码**。*Zixuan Zhang 和 Heng Ji*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.4.pdf)]\n3. **基于图注意力网络的事件时间抽取与传播**。*Haoyang Wen、Yanru Qu、Heng Ji、Qiang Ning、Jiawei Han、Avi Sil、Hanghang Tong 和 Dan Roth*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.6.pdf)]\n4. **SGL：通过多语言翻译讲述语义解析的图语言**。*Luigi Procopio、Rocco Tripodi 和 Roberto Navigli*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.30.pdf)]\n5. **用于上下文感知时序图生成的神经语言建模**。*Aman Madaan 和 Yiming Yang*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.67.pdf)]\n6. **用于不确定性知识图谱推理的概率盒嵌入**。*Xuelu Chen、Michael Boratko、Muhao Chen、Shib Sankar Dasgupta、Xiang Lorraine Li 和 Andrew McCallum*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.68.pdf)]\n7. **MTAG：用于未对齐的人类多模态语言序列的模态-时间注意力图**。*Jianing Yang、Yongxin Wang、Ruitao Yi、Yuying Zhu、Azaan Rehman、Amir Zadeh、Soujanya Poria 和 Louis-Philippe Morency*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.79.pdf)]\n8. **利用异质图注意力网络在共指消解中融合句法与语义**。*Fan Jiang 和 Trevor Cohn*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.125.pdf)]\n9. **基于图网络的可解释性病历诊断中的反事实支持事实抽取**。*Haoran Wu、Wei Chen、Shuang Xu 和 Bo Xu*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.156.pdf)]\n10. **利用知识图谱和整数线性规划生成最优面试问题方案**。*Soham Datta、Prabir Mallick、Sangameshwar Patil、Indrajit Bhattacharya 和 Girish Palshikar*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.160.pdf)]\n11. **教育数据中概念先修关系学习的异质图神经网络**。*Chenghao Jia、Yongliang Shen、Yechun Tang、Lu Sun 和 Weiming Lu*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.164.pdf)]\n12. **利用正交普罗克鲁斯特斯分析进行高效的知识图谱嵌入学习**。*Xutan Peng、Guanyi Chen、Chenghua Lin 和 Mark Stevenson*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.187.pdf)]\n13. **使用线性时间正则化器和多向量嵌入进行时序知识图谱补全**。*Chengjin Xu、Yung-Yu Chen、Mojtaba Nayyeri 和 Jens Lehmann*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.202.pdf)]\n14. **Edge：用外部文本丰富知识图谱嵌入**。*Saed Rezayi、Handong Zhao、Sungchul Kim、Ryan Rossi、Nedim Lipka 和 Sheng Li*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.221.pdf)]\n15. **基于多个依存句树的图集成学习用于方面级情感分类**。*Xiaochen Hou、Peng Qi、Guangtao Wang、Rex Ying、Jing Huang、Xiaodong He 和 Bowen Zhou*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.229.pdf)]\n16. **基于类型感知的图卷积网络和层集成的方面级情感分析**。*Yuanhe Tian、Guimin Chen 和 Yan Song*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.231.pdf)]\n17. **具有丰富文档级结构的事件因果关系识别的图卷积网络**。*Minh Tran Phu 和 Thien Huu Nguyen*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.273.pdf)]\n18. **基于知识图谱的合成语料生成用于知识增强型语言模型预训练**。*Oshin Agarwal、Heming Ge、Siamak Shakeri 和 Rami Al-Rfou*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.278.pdf)]\n19. **用于文本分类的归纳主题变分图自编码器**。*Qianqian Xie、Jimin Huang、Pan Du、Min Peng 和 Jian-Yun Nie*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.333.pdf)]\n20. **高效总结多文档聚类的文本和图编码**。*Ramakanth Pasunuru、Mengwen Liu、Mohit Bansal、Sujith Ravi 和 Markus Dreyer*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.380.pdf)]\n21. **用基于实体的叙事图建模人类心理状态**。*I-Ta Lee、Maria Leonor Pacheco 和 Dan Goldwasser*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.391.pdf)]\n22. **ShadowGNN：用于文本到SQL解析器的图投影神经网络**。*Zhi Chen、Lu Chen、Yanbin Zhao、Ruisheng Cao、Zihan Xu、Su Zhu 和 Kai Yu*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002Fhttps:\u002F\u002Fgithub.com\u002FWowCZ\u002Fshadowgnn.pdf)]\n23. **RTFE：一种用于时序知识图谱补全的递归时间事实嵌入框架**。*Youri Xu、Haihong E、Meina Song、Wenyu Song、Xiaodong Lv、Wang Haotian 和 Yang Jinrui*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.451.pdf)]\n24. **用于多跳问答的广度优先推理图**。*Yongjie Huang 和 Meng Yang*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.464.pdf)]\n25. **改进知识图谱上多语言问答的零样本跨语言迁移**。*Yucheng Zhou、Xiubo Geng、Tao Shen、Wenqiang Zhang 和 Daxin Jiang*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.465.pdf)]\n26. **DAGN：用于逻辑推理的话语感知图网络**。*Yinya Huang、Meng Fang、Yu Cao、Liwei Wang 和 Xiaodan Liang*。***NAACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.467.pdf)]\n\n***ACL 2021***\n\n1. **基于多通道图神经网络的多模态情感检测**。*杨晓翠、冯石、张一飞和王大令*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.28.pdf)]\n2. **SocAoG：用于对话中社会关系推断的增量图解析**。*邱亮、梁源、赵义舟、陆攀、彭宝林、于洲、吴颖年和朱松纯*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.54.pdf)]\n3. **CitationIE：利用引用图进行科学信息抽取**。*Vijay Viswanathan、Graham Neubig和刘鹏飞*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.59.pdf)]\n4. **对照知识：结合外部知识的图神经网络假新闻检测**。*胡琳梅、杨天驰、张路浩、钟万军、唐渡宇、史川、段楠和周明*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.62.pdf)]\n6. **用于会话情感识别的有向无环图网络**。*沈伟洲、吴思悦、杨云逸和全晓俊*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.123.pdf)]\n7. **发现对话结构图以实现连贯的对话生成**。*徐俊、雷泽阳、王海峰、牛正宇、吴华和车万祥*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.136.pdf)]\n8. **鸟瞰视角：通过简单的信息论方法探测语言图结构**。*侯一凡和Mrinmaya Sachan*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.145.pdf)]\n9. **利用关系推理模式毒化知识图谱嵌入**。*Peru Bhardwaj、John Kelleher、Luca Costabello和Declan O’Sullivan*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.147.pdf)]\n10. **ExCAR：事件图知识增强的可解释因果推理**。*杜立、丁潇、熊凯、刘婷和秦冰*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.183.pdf)]\n11. **LGESQL：具有混合局部与非局部关系的线图增强型文本到SQL模型**。*曹瑞生、陈璐、陈志、赵彦斌、朱苏和于凯*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.198.pdf)]\n12. **利用相关性图学习句法密集嵌入以进行自动可读性评估**。*邱欣颖、陈元、陈汉武、聂建云、沈宇明和卢大伟*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.235.pdf)]\n13. **位置偏差缓解：一种面向情感原因抽取的知识感知图模型**。*闫瀚奇、桂林、Gabriele Pergola和何玉兰*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.261.pdf)]\n14. **将结构化情感分析视为依存句法解析**。*Jeremy Barnes、Robin Kurtz、Stephan Oepen、Lilja Øvrelid和Erik Velldal*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.263.pdf)]\n15. **迈向传播不确定性：用于谣言检测的边增强贝叶斯图卷积网络**。*魏凌伟、胡斗、周伟、岳昭娟和胡松林*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.297.pdf)]\n16. **用于多标签文本分类的标签特定双图神经网络**。*马倩雯、袁春元、周伟和胡松林*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.298.pdf)]\n17. **ABCD：将复杂句子转换为一组覆盖性简单句子的图框架**。*高延军、黄廷豪和Rebecca J. Passonneau*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.303.pdf)]\n18. **用于人格检测的心理语言三部图网络**。*杨涛、杨菲凡、欧阳浩兰和全晓俊*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.326.pdf)]\n19. **PairRE：基于成对关系向量的知识图谱嵌入**。*晁琳琳、何建山、王泰丰和楚伟*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.336.pdf)]\n20. **基于依存关系的注意力图卷积网络关系抽取**。*田远河、陈贵民、宋燕和万翔*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.344.pdf)]\n21. **知识图谱和注意力有何帮助？袋级关系抽取的定性分析**。*胡子坤、曹义新、黄利夫和Tat-Seng Chua*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.359.pdf)]\n22. **基于实体-动作-地点图的推理以理解程序性文本**。*黄浩、耿秀波、裴健、龙国栋和江大鑫*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.396.pdf)]\n23. **为溯因推理学习事件图知识**。*杜立、丁潇、刘婷和秦冰*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.403.pdf)]\n24. **对Softmax交叉熵和负采样的统一解释：以知识图谱嵌入为例**。*神上英隆和林克彦*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.429.pdf)]\n25. **MMGCN：通过深度图卷积网络进行多模态融合，用于会话中的情感识别**。*胡静文、刘雨辰、赵金明和金琴*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.440.pdf)]\n26. **BASS：利用统一语义图提升抽象摘要生成**。*吴文浩、李伟、肖欣妍、刘嘉晨、曹子强、李素坚、吴华和王海峰*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.472.pdf)]\n27. **用于基于方面的情感分析的双图卷积网络**。*李瑞凡、陈浩、冯方翔、马占宇、王晓杰和Eduard Hovy*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.494.pdf)]\n28. **采用高阶切比雪夫近似的多跳图卷积网络用于文本推理**。*姜书然、陈清才、刘欣、胡宝田和张丽赛*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.513.pdf)]\n30. **使用图注意力Transformer进行非任务导向对话生成时的空间高效上下文编码**。*Fabian Galetzka、Jewgeni Rose、David Schlangen和Jens Lehmann*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-long.546.pdf)]\n31. **利用异构图神经网络进行跨语言文本分类**。*王梓云、刘轩、杨培基、刘世兴和王志胜*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.78.pdf)]\n32. **通过联合利用状态和常识图表示实现高效的基于文本的强化学习**。*Keerthiram Murugesan、Mattia Atzeni、Pavan Kapanipathi、Kartik Talamadupula、Mrinmaya Sachan和Murray Campbell*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.91.pdf)]\n33. **利用图神经网络显式捕捉实体提及之间的关系，用于领域特定的命名实体识别**。*陈培、丁海波、荒木淳和黄瑞红*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.93.pdf)]\n34. **使用变分图自编码器进行无监督的跨领域先决条件链学习**。*Irene Li、Vanessa Yan、Tianxiao Li、Qu Rihao和Dragomir Radev*。***ACL 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.acl-short.127.pdf)]\n\n***EMNLP 2021***\n\n1. **用于抽取式文本摘要的多层图神经网络**。*景宝宇、游泽宇、杨涛、范伟和童航航*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.11.pdf)]\n2. **基于贝塔分布引导的方面感知图，结合情感知识进行方面类别情感分析**。*梁斌、苏航、尹荣迪、桂琳、杨敏、赵琴、于晓琪和徐瑞峰*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.19.pdf)]\n3. **基于对话中轮次上下文表示的图神经网络**。*李奉锡和崔永淑*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.36.pdf)]\n4. **扩展而非重建：将条件图修改表述为自回归序列标注问题**。*莱昂·韦伯、扬内斯·门希迈耶、萨穆埃莱·加尔达和乌尔夫·莱瑟*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.93.pdf)]\n5. **CR-Walker：面向会话推荐的树状图推理与对话行为模型**。*马文畅、高信隆和黄民列*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.139.pdf)]\n6. **CSAGN：面向会话语义角色标注的会话结构感知图网络**。*吴汉、徐坤和宋林琦*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.177.pdf)]\n7. **构建有向语义图以实现连贯的长文本生成**。*王子傲、张晓峰和杜宏伟*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.200.pdf)]\n8. **用于关键短语生成的异构图神经网络**。*叶嘉诚、蔡睿健、桂涛和张琪*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.213.pdf)]\n9. **基于关键词图的弱监督文本分类**。*张璐、丁建东、许毅、刘英瑶和周水耕*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.222.pdf)]\n10. **面向短文本分类的层次化异构图表示学习**。*王雅清、王松、姚全明和窦德静*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.247.pdf)]\n11. **GraphMR：用于数学推理的图神经网络**。*冯伟杰、刘彬彬、徐东鹏、郑启龙和徐云*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.273.pdf)]\n12. **利用相互引导和句间关系图进行论点对抽取**。*鲍建柱、梁斌、孙静怡、张一策、杨敏和徐瑞峰*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.319.pdf)]\n13. **基于事件图的句子融合**。*袁瑞峰、王子力和李文杰*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.334.pdf)]\n14. **TransferNet：一种高效透明的框架，用于在关系图上进行多跳问答**。*史佳欣、曹书林、侯磊、李娟子和张翰旺*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.341.pdf)]\n17. **未来并非一维的：通过图模型进行复杂事件模式归纳以实现事件预测**。*李曼玲、李莎、王振海龙、黄立夫、曹京贤、季恒、韩家伟和克莱尔·沃斯*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.422.pdf)]\n20. **基于时间感知最优传输的事件图压缩技术的时间线摘要**。*李曼玲、马腾飞、余墨、吴凌飞、高天、季恒和凯瑟琳·麦金恩*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.519.pdf)]\n21. **ExplaGraphs：面向结构化常识推理的解释图生成任务**。*斯瓦尔纳迪普·萨哈、普拉蒂克·亚达夫、丽莎·鲍尔和莫希特·班萨尔*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.609.pdf)]\n24. **通过序列到图转换及强化图精炼实现高效思维导图生成**。*胡梦婷、郭洪雷、赵世万、高航和苏忠*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.641.pdf)]\n25. **用于文本分类的深度注意力扩散图神经网络**。*刘永浩、关仁初、法乌斯托·久恩奇利亚、梁延春和冯晓月*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.642.pdf)]\n28. **用于神经机器翻译的文档图**。*徐明洲、李良友、Derek F. Wong、刘群和Lidia S. Chao*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.663.pdf)]\n29. **用于多平行词对齐的图算法**。*阿尤布·伊玛尼古加里、马苏德·贾利利·萨贝特、卢特菲·凯雷姆·塞内尔、菲利普·杜夫特、弗朗索瓦·伊冯和欣里希·舒茨*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.665.pdf)]\n31. **用于AMR解析的图分割与对齐的可微松弛方法**。*吕春川、谢伊·B·科恩和伊万·季托夫*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.714.pdf)]\n34. **利用声明引导的层次化图注意力网络在Twitter上进行谣言检测**。*林宏展、马静、程明飞、杨志伟、陈亮亮和陈光*。***EMNLP 2021*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.emnlp-main.786.pdf)]\n\n\n***ACL 2022***\n\n1. **用于多领域对话状态跟踪的动态模式图融合网络**。*Yue Feng、Aldo Lipani、Fanghua Ye、Qiang Zhang 和 Emine Yilmaz*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.10.pdf)]\n2. **基于自监督自适应图对齐的多语言知识图谱补全**。*Zijie Huang、Zheng Li、Haoming Jiang、Tianyu Cao、Hanqing Lu、Bing Yin、Karthik Subbian、Yizhou Sun 和 Wei Wang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.36.pdf)]\n4. **面向程序化多模态机器理解的时间—模态实体图建模**。*Huibin Zhang、Zhengkun Zhang、Yao Zhang、Jun Wang、Yufan Li、Ning Jiang、Xin Wei 和 Zhenglu Yang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.84.pdf)]\n5. **基于预训练语言模型的解释图生成：结合对比学习的实证研究**。*Swarnadeep Saha、Prateek Yadav 和 Mohit Bansal*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.85.pdf)]\n6. **利用图神经网络持续改进社交情境表示以应对虚假新闻检测**。*Nikhil Mehta、Maria Pacheco 和 Dan Goldwasser*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.97.pdf)]\n7. **基于跨模态图卷积网络的多模态讽刺检测**。*Bin Liang、Chenwei Lou、Xiang Li、Min Yang、Lin Gui、Yulan He、Wenjie Pei 和 Ruifeng Xu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.124.pdf)]\n8. **通过异质语言学图增强中文预训练语言模型**。*Yanzeng Li、Jiangxia Cao、Xin Cong、Zhenyu Zhang、Bowen Yu、Hongsong Zhu 和 Tingwen Liu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.140.pdf)]\n9. **在细粒度实体类型标注中，借助可扩展图推理从兄弟提及中学习**。*Yi Chen、Jiayang Cheng、Haiyun Jiang、Lemao Liu、Haisong Zhang、Shuming Shi 和 Ruifeng Xu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.147.pdf)]\n10. **知识图谱嵌入的高效超参数搜索**。*Yongqi Zhang、Zhanke Zhou、Quanming Yao 和 Yong Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.194.pdf)]\n11. **变分图自动编码作为 AMR 共指消解的廉价监督**。*Irene Li、Linfeng Song、Kun Xu 和 Dong Yu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.199.pdf)]\n12. **序列到序列的知识图谱补全与问答**。*Apoorv Saxena、Adrian Kochsiek 和 Rainer Gemulla*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.201.pdf)]\n13. **CAKE：一种可扩展的常识感知多视角知识图谱补全框架**。*Guanglin Niu、Bo Li、Yongfei Zhang 和 Shiliang Pu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.205.pdf)]\n14. **用于方面情感三元组抽取的增强型多通道图卷积网络**。*Hao Chen、Zepeng Zhai、Fangxiang Feng、Ruifan Li 和 Xiaojie Wang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.212.pdf)]\n15. **文本分类中的词袋、图与序列：质疑文本图的必要性及宽 MLP 的惊人实力**。*Lukas Galke 和 Ansgar Scherp*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.279.pdf)]\n16. **采用新颖标签策略进行结构化情感分析的有效标记图建模**。*Wenxuan Shi、Fei Li、Jingye Li、Hao Fei 和 Donghong Ji*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.291.pdf)]\n17. **SimKGC：基于预训练语言模型的简单对比式知识图谱补全**。*Liang Wang、Wei Zhao、Zhuoyu Wei 和 Jingming Liu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.295.pdf)]\n18. **用于放射学发现摘要的图增强对比学习**。*Jinpeng Hu、Zhuo Li、Zhihong Chen、Zhen Li、Xiang Wan 和 Tsung-Hui Chang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.320.pdf)]\n19. **无监督依存句法图网络**。*Yikang Shen、Shawn Tan、Alessandro Sordoni、Peng Li、Jie Zhou 和 Aaron Courville*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.327.pdf)]\n20. **KG-FiD：将知识图谱注入解码器融合以实现开放域问答**。*Donghan Yu、Chenguang Zhu、Yuwei Fang、Wenhao Yu、Shuohang Wang、Yichong Xu、Xiang Ren、Yiming Yang 和 Michael Zeng*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.340.pdf)]\n21. **HeterMPC：一种用于多方对话中回复生成的异质图神经网络**。*Jia-Chen Gu、Chao-Hong Tan、Chongyang Tao、Zhen-Hua Ling、Huang Hu、Xiubo Geng 和 Daxin Jiang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.349.pdf)]\n22. **RotateQVS：将时间信息表示为四元数向量空间中的旋转，用于时间知识图谱补全**。*Kai Chen、Ye Wang、Yitong Li 和 Aiping Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.402.pdf)]\n23. **基于文本蕴含与软传递性的蕴涵图学习**。*Zhibin Chen、Yansong Feng 和 Dongyan Zhao*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.406.pdf)]\n24. **用于 AMR 解析与生成的图预训练**。*Xuefeng Bai、Yulong Chen 和 Yue Zhang*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.415.pdf)]\n25. **AdaLoGN：用于基于推理的机器阅读理解的自适应逻辑图网络**。*Xiao Li、Gong Cheng、Ziheng Chen、Yawei Sun 和 Yuzhong Qu*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.494.pdf)]\n26. **结合上下文向量化与图微调以改进词嵌入**。*Jiangbin Zheng、Yile Wang、Ge Wang、Jun Xia、Yufei Huang、Guojiang Zhao、Yue Zhang 和 Stan Li*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-long.561.pdf)]\n27. **用于时间知识图谱推理的复杂演化模式学习**。*Zixuan Li、Saiping Guan、Xiaolong Jin、Weihua Peng、Yajuan Lyu、Yong Zhu、Long Bai、Wei Li、Jiafeng Guo 和 Xueqi Cheng*。***ACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-short.32.pdf)]\n28. **CogKGE：一个用于表示多源异质知识的知识图谱嵌入工具包及基准测试平台**。*Zhuoran Jin、Tianyi Men、Hongbang Yuan、Zhitao He、Dianbo Sui、Chenhao Wang、Zhipeng Xue、Yubo Chen 和 Jun Zhao*。***ACL 2022 展示会*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-demo.16.pdf)]\n29. **MMEKG：面向跨模态通用表示的多模态事件知识图谱**。*Yubo Ma、Zehao Wang、Mukai Li、Yixin Cao、Meiqi Chen、Xinze Li、Wenqi Sun、Kunquan Deng、Kun Wang、Aixin Sun 和 Jing Shao*。***ACL 2022 展示会*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.acl-demo.23.pdf)]\n\n***NAACL 2022***\n1. **基于事件图推理的跨文档虚假信息检测**。*吴雪晴、黄恭祥、冯毅和季恒*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.40.pdf)]\n2. **DocTime：文档级时序依赖图解析器**。*普尼特·马图尔、弗拉德·莫拉里乌、维雷娜·凯尼格-菲特考、顾久翔、弗兰克·德农库尔、全陈、阿妮·嫩科娃、迪内什·马诺查和拉吉夫·贾因*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.73.pdf)]\n3. **用于自动短答案评分的多关系图变换器**。*拉贾特·阿加瓦尔、瓦伦·库拉纳、卡里什·格罗弗、穆克什·莫哈尼亚和维克拉姆·戈亚尔*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.146.pdf)]\n4. **利用双重图自编码器进行事件模式归纳**。*金晓梦、李曼玲和季恒*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.147.pdf)]\n5. **学习借用——知识图谱补全中未提及实体对的关系表示**。*胡达·哈卡米、莫娜·哈卡米、安格罗什·曼迪亚和达努什卡·博莱加拉*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.209.pdf)]\n6. **FactGraph：基于语义图表示的摘要事实性评估**。*莱昂纳多·里贝罗、刘孟文、伊琳娜·古列维奇、马库斯·德赖尔和莫希特·班萨尔*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.236.pdf)]\n7. **基于视频场景图的动态多步推理用于视频问答**。*毛建国、蒋文斌、王向东、冯志凡、吕雅娟、刘宏和朱勇*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.286.pdf)]\n8. **基于联合学习的异构图注意力网络用于时间线摘要生成**。*游静怡、李东源、上垣英孝、船越浩太郎和奥村学*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.301.pdf)]\n9. **SSEGCN：面向方面情感分析的句法与语义增强图卷积网络**。*张政、周子力和王燕娜*。***NAACL 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.naacl-main.362.pdf)]\n\n***COLING 2022***\n1. **TopKG：基于知识图谱全局规划的目标导向对话**。*杨志通、王博、周金峰、谭岳、赵东明、黄坤、何瑞芳和侯月仙*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.62.pdf)]\n2. **层次信息的重要性：基于树状图神经网络的文本分类**。*张冲、朱赫、彭星宇、吴俊然和许科*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.79.pdf)]\n3. **ConTextING：为归纳式文本分类的图神经网络赋予文档级别的上下文嵌入**。*黄彦豪、陈怡欣和陈奕信*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.100.pdf)]\n5. **面向知识感知问答的动态相关性图网络**。*郑晨和帕丽萨·科尔贾姆希迪*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.116.pdf)]\n8. **基于语义结构的知识图谱问答查询图预测**。*李明辰和季世浩*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.135.pdf)]\n11. **利用双关系图注意力网络进行事件检测**。*米佳鑫、胡波和李鹏*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.172.pdf)]\n13. **ERGO：用于文档级事件因果识别的事件关系图变换器**。*陈美琪、曹艺欣、邓坤权、李牧凯、王坤、邵静和张燕*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.185.pdf)]\n18. **Doc-GCN：用于文档版面分析的异质图卷积网络**。*罗思文、丁一昊、龙思渠、乔赛亚·潘和韩素妍*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.256.pdf)]\n23. **基于图变换的通用依存关系透明语义解析**。*韦塞尔·波尔曼、里克·范诺德和约翰·博斯*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.367.pdf)]\n24. **GraDA：用于常识推理的图生成式数据增强**。*阿迪亚莎·马哈拉纳和莫希特·班萨尔*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.397.pdf)]\n26. **考虑拓扑不平衡与关系真实性的问题导向层次图注意力网络用于假新闻检测**。*高力、宋凌云、刘杰、陈博林和商雪群*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.415.pdf)]\n29. **多层级社区意识图神经网络用于神经机器翻译**。*阮彬、阮隆和丁 Dien*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.444.pdf)]\n31. **用于抽取式长文档摘要的多图神经网络**。*段宣勇、阮黎明和裴克怀南*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.512.pdf)]\n32. **基于图神经网络的自动文本摘要综述**。*马可·费迪南德·萨尔赫纳和亚当·雅托特*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.536.pdf)]\n33. **HeterGraphLongSum：结合片段聚合的异质图神经网络用于抽取式长文档摘要**。*潘端英、阮玉蓉和裴克怀南*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.545.pdf)]\n34. **GRETEL：用于长文档抽取式摘要的图对比主题增强语言模型**。*谢倩倩、黄继敏、图莉卡·萨哈和索菲娅·阿纳尼亚杜*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.546.pdf)]\n35. **社交机器人感知图神经网络用于早期谣言检测**。*黄振、吕志龙、韩晓云、李彬阳、陆孟龙和李东升*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.580.pdf)]\n36. **基于组合的异质图多通道注意力网络用于多方面多情感分类**。*牛浩、熊云、高健、缪中臣、王小苏、任洪润、张瑶和朱阳永*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.594.pdf)]\n37. **可学习的依存关系驱动双重图结构用于方面级情感分析**。*马英龙和庞云鹤*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.618.pdf)]\n38. **建模模态内与模态间关系：用于多模态情感分析的层次图对比学习**。*林子杰、梁斌、龙云飞、党义学、杨敏、张敏和徐瑞峰*。***COLING 2022*** [[pdf](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2022.coling-1.622.pdf)]\n\n\n\n\n## 综合图神经网络论文列表\n\n[thunlp\u002FGNNPapers](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers)\n\n[naganandy\u002Fgraph-based-deep-learning-literature](https:\u002F\u002Fgithub.com\u002Fnaganandy\u002Fgraph-based-deep-learning-literature)\n\n[nnzhan\u002FAwesome-Graph-Neural-Networks](https:\u002F\u002Fgithub.com\u002Fnnzhan\u002FAwesome-Graph-Neural-Networks)\n\n## 教程\n\n[EMNLP 2019 GNNs-for-NLP](https:\u002F\u002Fgithub.com\u002Fsvjan5\u002FGNNs-for-NLP)\n\n[CS224W：图上的机器学习](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224w\u002Findex.html#content)\n\n## 工具\n\n[深度图库（DGL）](https:\u002F\u002Fgithub.com\u002Fdmlc\u002Fdgl)\n\n[PyTorch几何（PyG）](https:\u002F\u002Fgithub.com\u002Frusty1s\u002Fpytorch_geometric)\n\n## 学位论文\n\n《基于图结构表示的自然语言处理与文本挖掘》（阿尔伯塔大学），刘邦，阿尔伯塔大学。\n\n《基于图结构表示的深度学习》（阿姆斯特丹大学），托马斯·诺伯特·基普夫。\n\n《用于自然语言处理的神经图嵌入方法》（印度科学研究所），希卡尔·瓦西什特。\n\n《深度神经网络中结构的复兴》（剑桥大学），佩塔尔·韦利奇科维奇。","# GNN4NLP-Papers 快速上手指南\n\n**GNN4NLP-Papers** 并非一个可执行的软件工具或代码库，而是一个**学术论文清单资源库**。它系统地整理了将图神经网络（GNN）方法应用于自然语言处理（NLP）领域的最新研究论文。\n\n因此，本指南旨在指导开发者如何快速获取、浏览和利用该资源库中的文献信息，而非进行软件安装。\n\n## 1. 环境准备\n\n由于本项目本质是一个托管在 GitHub 上的文档列表，对环境要求极低：\n\n*   **操作系统**：Windows, macOS, Linux 均可。\n*   **前置依赖**：\n    *   现代网页浏览器（推荐 Chrome, Edge, Firefox）。\n    *   （可选）`git` 命令行工具：如果你希望将列表克隆到本地离线查看。\n    *   （可选）PDF 阅读器：用于阅读论文原文。\n\n## 2. 获取步骤\n\n你可以通过以下两种方式访问该资源：\n\n### 方式一：在线浏览（推荐）\n直接访问 GitHub 仓库页面，无需任何安装步骤。\n*   **地址**: `https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FGNN4NLP-Papers` (注：根据 README 中的代码链接推断所属组织，通常直接在 GitHub 搜索项目名即可)\n\n### 方式二：本地克隆\n如果你希望在本地维护或离线查看，可以使用 `git` 克隆仓库：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fmalllabiisc\u002FGNN4NLP-Papers.git\ncd GNN4NLP-Papers\n```\n\n*(注：如果原仓库地址不可达，请直接在 GitHub 搜索 \"GNN4NLP-Papers\" 获取最新镜像)*\n\n## 3. 基本使用\n\n该仓库的核心价值在于其分类清晰的论文索引。以下是使用流程：\n\n### 第一步：确定研究领域\n打开 `README.md` 文件，根据 **Taxonomy (分类体系)** 找到你感兴趣的方向。目前主要包含以下类别：\n*   **Fundamental NLP Tasks**: 基础任务（如词嵌入、指代消解、AMR 解析）。\n*   **Text Classification**: 文本分类（如短文本分类、少样本学习、多标签分类）。\n*   **Sentiment Analysis**: 情感分析（如方面级情感分类）。\n*   **Question Answering**: 问答系统（如多跳推理、事实核查）。\n*   **Information Extraction**: 信息抽取（如关系抽取、联合抽取）。\n*   **Text Generation**: 文本生成。\n\n### 第二步：查找目标论文\n在每个分类下，论文按时间倒序或重要性排列。每条记录包含：\n*   **标题**：论文名称。\n*   **作者**：研究团队。\n*   **会议\u002F年份**：发表 venue（如 ACL 2022, EMNLP 2021）。\n*   **链接**：\n    *   `[[pdf]]`: 指向论文全文（通常是 arXiv 或 ACL Anthology）。\n    *   `[[code]]`: 指向开源代码实现（如果有）。\n\n### 第三步：获取资源示例\n假设你想研究 **\"方面级情感分析 (Aspect-based Sentiment Analysis)\"** 并使用 **GCN** 方法：\n\n1.  滚动至 **Sentiment Analysis** 章节。\n2.  找到第一条记录：\n    > **Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks**. *Chen Zhang, et al.* **EMNLP 2019** [[pdf](...)] [[code](https:\u002F\u002Fgithub.com\u002FGeneZC\u002FASGCN)]\n3.  点击 `[[code]]` 链接跳转到具体的代码仓库。\n4.  进入该代码仓库后，参照其独立的 `README` 进行环境配置和运行（例如：`pip install -r requirements.txt`）。\n\n### 提示\n*   **追踪最新进展**：关注仓库顶部的徽章（Badges），如 `Newest: COLING-2022`，了解最近更新的会议论文。\n*   **代码复现**：并非所有列出的论文都提供了代码。请优先选择带有 `[[code]]` 标记的条目进行实验。","某自然语言处理团队的算法工程师正在研发一款针对中文医疗领域的命名实体识别（NER）系统，急需引入图神经网络（GNN）来融合词汇与句法信息以提升模型精度。\n\n### 没有 GNN4NLP-Papers 时\n- **文献检索大海捞针**：需要在 ACL、EMNLP、COLING 等十几个顶级会议的海量论文中手动筛选，耗时数周仍难以找全关于\"GNN+NLP\"的最新成果。\n- **复现资源缺失**：找到论文后，往往发现缺少对应的开源代码链接或数据集指引，导致验证想法的成本极高，甚至被迫放弃某些前沿思路。\n- **技术脉络模糊**：缺乏系统的分类索引，难以厘清从基础的词嵌入增强到复杂的异构图注意力网络等技术演进路线，容易在过时的方法上浪费精力。\n- **领域适配困难**：难以快速定位专门针对中文场景（如基于词典的 GNN）或特定任务（如少样本文本分类）的定制化解决方案。\n\n### 使用 GNN4NLP-Papers 后\n- **一站式精准获取**：直接查阅按任务分类的清单，瞬间锁定如 EMNLP 2019 关于中文 NER 的图神经网络论文及最新 COLING 2022 成果，调研效率提升十倍。\n- **代码与论文联动**：每条记录均附带官方代码仓库链接（如 WordGCN、RGCN-with-BERT），工程师可立即克隆运行，快速验证基线效果。\n- **清晰的技术图谱**：通过“基础任务”与“文本分类”等 taxonomy 结构，迅速掌握如何利用异构图增强预训练语言模型，明确技术选型方向。\n- **场景化方案匹配**：快速发现针对“细粒度实体类型”或“半监督短文本分类”的现成架构，直接将其迁移至医疗数据场景进行微调。\n\nGNN4NLP-Papers 将原本分散杂乱的学术资源转化为结构化的研发加速器，让团队能站在最新研究肩膀上快速落地高性能模型。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FIndexFziQ_GNN4NLP-Papers_615a7c11.png","IndexFziQ","Yuqiang Xie","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FIndexFziQ_2ccf6539.jpg","LLM Researcher @SkyworkAI. Ph.D. in NLP from IIE, CAS.","SkyworkAI","Beijing, China","IndexFziQ@gmail.com","yuqiang-xie.github.io","https:\u002F\u002Fgithub.com\u002FIndexFziQ",null,906,137,"2026-03-20T11:49:41","MIT",5,"","未说明",{"notes":94,"python":92,"dependencies":95},"该仓库并非一个可运行的软件工具或代码库，而是一个关于图神经网络（GNN）在自然语言处理（NLP）领域应用的论文列表合集。README 中列出了多篇学术论文的标题、作者、会议来源及链接，部分条目提供了指向外部独立代码仓库的链接，但本仓库本身不包含需要安装环境、依赖库或硬件资源的源代码。因此，不存在特定的操作系统、GPU、内存、Python 版本或依赖库需求。",[],[27,16],[98,99,100,101,102,103,104,105,106,107,108],"graph-neural-network","natural-language-processing","graph-convolutional-networks","question-answering","paperlist","knowledge-graph","knowledge-representation","knowledge-based-systems","graph-attention-network","heterogeneous-graphs","paper-list",4,"2026-03-27T02:49:30.150509","2026-04-11T18:33:04.968678",[],[]]