创业公司

• 机器学习、深度学习、计算机视觉、大数据创业公司 - Startups in AI

深度强化学习

• David Silver. "Tutorial: Deep Reinforcement Learning." ICML 2016.
• David Silver 的课程. "Reinforcement Learning". 2015.
• Bahdanau, Dzmitry, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron Courville, and Yoshua Bengio. "An Actor-Critic Algorithm for Sequence Prediction." arXiv preprint arXiv:1607.07086 (2016).
• Li, Jiwei, Will Monroe, Alan Ritter, and Dan Jurafsky. "Deep Reinforcement Learning for Dialogue Generation." arXiv preprint arXiv:1606.01541 (2016).
• Pathak, Deepak, Pulkit Agrawal, Alexei A. Efros, and Trevor Darrell. "Curiosity-driven Exploration by Self-supervised Prediction." arXiv preprint arXiv:1705.05363 (2017).
• Keneshloo, Yaser, Tian Shi, Chandan K. Reddy, and Naren Ramakrishnan. "Deep Reinforcement Learning For Sequence to Sequence Models." arXiv preprint arXiv:1805.09461 (2018).

对话系统

• Jiang, Shaojie, and Maarten de Rijke. "Why are Sequence-to-Sequence Models So Dull?." report, 2018.
• Eric Chu, Prashanth Vijayaraghavan, Deb Roy. "Learning Personas from Dialogue with Attentive Memory Networks." EMNLP (2018).
• Ruizhe Li, Chenghua Lin, Matthew Collinson, Xiao Li, Guanyi Chen. "A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification." arXiv:1810.09154 (2018).

任务导向型对话

• Wen, Tsung-Hsien, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. "A network-based end-to-end trainable task-oriented dialogue system." arXiv preprint arXiv:1604.04562 (2016).
• Li, Xiujun, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. "End-to-end task-completion neural dialogue systems." arXiv preprint arXiv:1703.01008 (2017).
• Li, Xiujun, Zachary C. Lipton, Bhuwan Dhingra, Lihong Li, Jianfeng Gao, and Yun-Nung Chen. "A user simulator for task-completion dialogues." arXiv preprint arXiv:1612.05688 (2016).
• Yan, Zhao, Nan Duan, Peng Chen, Ming Zhou, Jianshe Zhou, and Zhoujun Li. "Building Task-Oriented Dialogue Systems for Online Shopping." In AAAI, pp. 4618-4626. 2017.
• Peng, Baolin, Xiujun Li, Jianfeng Gao, Jingjing Liu, and Kam-Fai Wong. "Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning." ACL, vol. 1, pp. 2182-2192. 2018.
• Janarthanan Rajendran, Jatin Ganhotra, Satinder Singh, Lazaros Polymenakos. "Learning End-to-End Goal-Oriented Dialog with Multiple Answers." arXiv preprint arXiv:1808.09996 (2018).

文本生成

• Rennie, Steven J., Etienne Marcheret, Youssef Mroueh, Jarret Ross, and Vaibhava Goel. "Self-critical sequence training for image captioning." arXiv preprint arXiv:1612.00563 (2016).
• Lin, Kevin, Dianqi Li, Xiaodong He, Zhengyou Zhang, and Ming-Ting Sun. "Adversarial Ranking for Language Generation." arXiv preprint arXiv:1705.11001 (2017).
• Zhang, Li, Flood Sung, Feng Liu, Tao Xiang, Shaogang Gong, Yongxin Yang, and Timothy M. Hospedales. "Actor-Critic Sequence Training for Image Captioning." arXiv preprint arXiv:1706.09601 (2017).
• Wiseman, Sam, Stuart M. Shieber, and Alexander M. Rush. "Challenges in Data-to-Document Generation." arXiv preprint arXiv:1707.08052 (2017).
• Lebret, Rémi, David Grangier, and Michael Auli. "Neural text generation from structured data with application to the biography domain." arXiv preprint arXiv:1603.07771 (2016).
• Chisholm, Andrew, Will Radford, and Ben Hachey. "Learning to generate one-sentence biographies from Wikidata." arXiv preprint arXiv:1702.06235 (2017).
• Sha, Lei, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, and Zhifang Sui. "Order-Planning Neural Text Generation From Structured Data." arXiv preprint arXiv:1709.00155 (2017).
• Jiaxian Guo, Sidi Lu, Han Cai, Weinan Zhang, Yong Yu, Jun Wang. "Long Text Generation via Adversarial Training with Leaked Information." arXiv preprint arXiv:1709.08624 (2017).
• Guu, Kelvin, Tatsunori B. Hashimoto, Yonatan Oren, and Percy Liang. "Generating Sentences by Editing Prototypes." arXiv preprint arXiv:1709.08878 (2017).
• Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui. "Table-to-text Generation by Structure-aware Seq2seq Learnings." arXiv preprint arXiv:1711.09724 (2017).
• Kahou, Samira Ebrahimi, Adam Atkinson, Vincent Michalski, Akos Kadar, Adam Trischler, and Yoshua Bengio. "FigureQA: An Annotated Figure Dataset for Visual Reasoning." arXiv preprint arXiv:1710.07300 (2017).
• Murakami, Soichiro, Akihiko Watanabe, Akira Miyazawa, Keiichi Goshima, Toshihiko Yanase, Hiroya Takamura, and Yusuke Miyao. "Learning to Generate Market Comments from Stock Prices." In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol. 1, pp. 1374-1384. 2017.
• Mueller, Jonas, David Gifford, and Tommi Jaakkola. "Sequence to better sequence: continuous revision of combinatorial structures." In International Conference on Machine Learning, pp. 2536-2544. 2017.
• Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer. "Generating Wikipedia by Summarizing Long Sequences." ICLR 2018.
• Clark, Elizabeth, Anne Spencer Ross, Chenhao Tan, Yangfeng Ji, and Noah A. Smith. "Creative Writing with a Machine in the Loop: Case Studies on Slogans and Stories." (2018).
• Gehrmann, Sebastian, S. E. A. S. Harvard, Falcon Z. Dai, Henry Elder, and Alexander M. Rush. "End-to-End Content and Plan Selection for Natural Language Generation."
• Juncen Li, Robin Jia, He He, Percy Liang. "Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer." arXiv:1804.06437 2018.
• Yi Liao, Lidong Bing, Piji Li, Shuming Shi, Wai Lam, Tong Zhang. "Incorporating Pseudo-Parallel Data for Quantifiable Sequence Editing." arXiv:1804.07007 2018.
• Xin Wang, Wenhu Chen, Yuan-Fang Wang, William Yang Wang. "No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling." arXiv:1804.09160 2018.
• Sam Wiseman, Stuart M. Shieber, Alexander M. Rush. "Learning Neural Templates for Text Generation ." arXiv:1808.10122 2018.

文本摘要

• Ryang, Seonggi 和 Takeshi Abekawa。"使用强化学习的自动文本摘要框架。" 载于《2012年自然语言处理经验方法会议与计算自然语言学习联合会议论文集》，第256-265页。计算语言学协会，2012年。[非基于神经网络的方法]
• King, Ben, Rahul Jha, Tyler Johnson, Vaishnavi Sundararajan 和 Clayton Scott。"使用深度神经网络的自动文本摘要实验。" 机器学习（2011年）。
• Liu, Yan, Sheng-hua Zhong 和 Wenjie Li。"通过无监督深度学习的面向查询的多文档摘要。" AAAI。2012年。
• Rioux, Cody, Sadid A. Hasan 和 Yllias Chali。"Fear the REAPER: 一个使用强化学习的自动多文档摘要系统。" 载于EMNLP，第681-690页。2014年。[非基于神经网络的方法]
• PadmaPriya, G. 和 K. Duraiswamy。"一种使用深度学习算法的文本摘要方法。" 计算机科学杂志 10, 第1期（2013年）：1-9。
• Denil, Misha, Alban Demiraj 和 Nando de Freitas。"从标记文档中提取显著句子。" arXiv预印本 arXiv:1412.6815 (2014年)。
• Kågebäck, Mikael 等人。"使用连续向量空间模型的抽取式摘要。" 第二届连续向量空间模型及其组合性研讨会（CVSC）@ EACL论文集。2014年。
• Denil, Misha, Alban Demiraj, Nal Kalchbrenner, Phil Blunsom 和 Nando de Freitas。"使用单一卷积神经网络建模、可视化和摘要文档。" arXiv预印本 arXiv:1406.3830 (2014年)。
• Cao, Ziqiang, Furu Wei, Li Dong, Sujian Li 和 Ming Zhou。"使用递归神经网络的排序及其在多文档摘要中的应用。" (AAAI'2015)。
• Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh 和 Noah A. Smith。"使用语义表示进行抽象摘要。" NAACL 2015。
• Wenpeng Yin, Yulong Pei。"优化文档摘要的句子建模和选择。" IJCAI 2015。
• He, Zhanying, Chun Chen, Jiajun Bu, Can Wang, Lijun Zhang, Deng Cai 和 Xiaofei He。"基于数据重建的文档摘要。" 载于AAAI。2012年。
• Liu, He, Hongliang Yu 和 Zhi-Hong Deng。"基于两级稀疏表示模型的多文档摘要。" 载于第二十九届AAAI人工智能会议。2015年。
• Jin-ge Yao, Xiaojun Wan, Jianguo Xiao。"通过稀疏优化的压缩文档摘要。" IJCAI 2015。
• Piji Li, Lidong Bing, Wai Lam, Hang Li 和 Yi Liao。"通过稀疏编码的读者感知多文档摘要。" IJCAI 2015。
• Lopyrev, Konstantin。"使用循环神经网络生成新闻标题。" arXiv预印本 arXiv:1512.01712 (2015年)。[将第一段作为文档。]
• Alexander M. Rush, Sumit Chopra, Jason Weston。"用于抽象句子摘要的神经注意力模型。" EMNLP 2015。[句子压缩]
• Hu, Baotian, Qingcai Chen 和 Fangze Zhu。"LCSTS: 一个大规模中文短文本摘要数据集。" arXiv预印本 arXiv:1506.05865 (2015年)。
• Gulcehre, Caglar, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou 和 Yoshua Bengio。"指向未知词。" arXiv预印本 arXiv:1603.08148 (2016年)。
• Nallapati, Ramesh, Bing Xiang 和 Bowen Zhou。"使用序列到序列RNN及更高阶方法的抽象文本摘要。" arXiv预印本 arXiv:1602.06023 (2016年)。[句子压缩]
• Sumit Chopra, Alexander M. Rush 和 Michael Auli。"使用注意力循环神经网络的抽象句子摘要" NAACL 2016。
• Jiatao Gu, Zhengdong Lu, Hang Li, Victor O.K. Li。"在序列到序列学习中融入复制机制。" ACL。(2016年)
• Jianpeng Cheng, Mirella Lapata。"通过提取句子和词语的神经摘要"。 ACL。(2016年)
• Zhang, Jianmin, Jin-ge Yao 和 Xiaojun Wan。"从实时文本评论构建体育新闻。" 载于ACL论文集。2016年。
• Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei。"AttSum: 使用神经注意力联合学习聚焦和摘要"。 arXiv:1604.00125 (2016年)
• Ayana, Shiqi Shen, Zhiyuan Liu, Maosong Sun。"具有句子级优化的神经标题生成"。 arXiv:1604.01904 (2016年)
• Kikuchi, Yuta, Graham Neubig, Ryohei Sasano, Hiroya Takamura 和 Manabu Okumura。"在神经编码器-解码器中控制输出长度。" arXiv预印本 arXiv:1609.09552 (2016年)。
• Qian Chen, Xiaodan Zhu, Zhenhua Ling, Si Wei 和 Hui Jiang。"用于文档摘要的基于分心的神经网络。" IJCAI 2016。
• Wang, Lu 和 Wang Ling。"基于神经网络的意见和论点抽象生成。" NAACL 2016。
• Yishu Miao, Phil Blunsom。"语言作为潜在变量：用于句子压缩的离散生成模型。" EMNLP 2016。
• Takase, Sho, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao 和 Masaaki Nagata。"基于抽象意义表示的神经标题生成。" EMNLP，第1054-1059页。2016年。
• Hongya Song, Zhaochun Ren, Piji Li, Shangsong Liang, Jun Ma 和 Maarten de Rijke。在非事实性社区问答中总结答案。 载于WSDM 2017：第十届网络搜索与数据挖掘国际会议，2017年。
• Wenyuan Zeng, Wenjie Luo, Sanja Fidler, Raquel Urtasun。"通过重读和复制机制进行高效摘要。" arXiv预印本 arXiv:1611.03382 (2016年)。
• Piji Li, Zihao Wang, Wai Lam, Zhaochun Ren, Lidong Bing。"通过变分自编码器进行多文档摘要的显著性估计"。 载于AAAI，2017年。
• Ramesh Nallapati, Feifei Zhai, Bowen Zhou。SummaRuNNer: 一个基于循环神经网络的序列模型，用于文档的抽取式摘要。 载于AAAI，2017年。
• Ramesh Nallapati, Bowen Zhou, Mingbo Ma。"分类或选择：用于抽取式文档摘要的神经架构。" arXiv预印本 arXiv:1611.04244 (2016年)。
• Suzuki, Jun 和 Masaaki Nagata。"为神经抽象摘要切断冗余重复生成。" EACL 2017 (2017年)：291。
• Jiwei Tan 和 Xiaojun Wan。基于图注意神经模型的抽象文档摘要。 ACL，2017年。
• Preksha Nema, Mitesh M. Khapra, Balaraman Ravindran 和 Anirban Laha。用于基于查询的抽象摘要的多样性驱动注意力模型。 ACL，2017年。
• Abigail See, Peter J. Liu 和 Christopher D. Manning。直击要点：使用指针生成器网络进行摘要。 ACL，2017年。
• Qingyu Zhou, Nan Yang, Furu Wei 和 Ming Zhou。用于抽象句子摘要的选择性编码。 ACL，2017年。
• Maxime Peyrard 和 Judith Eckle-Kohler。用于基于优化的多文档摘要的自动金字塔监督学习。 ACL，2017年。
• Shashi Narayan, Nikos Papasarantopoulos, Mirella Lapata, Shay B. Cohen。"具有辅助信息的神经抽取式摘要。" arXiv预印本 arXiv:1704.04530 (2017年)。
• Romain Paulus, Caiming Xiong, Richard Socher。"用于抽象摘要的深度强化模型。" (2017年)。
• Shibhansh Dohare, Harish Karnick。"使用抽象意义表示的文本摘要。" arXiv:1706.01678 (2017年)。
• Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan, Dragomir Radev。"基于图的神经多文档摘要。" arXiv:1706.06681 (2017年)。
• Piji Li, Wai Lam, Lidong Bing 和 Zihao Wang。用于抽象文本摘要的深度循环生成解码器。 自然语言处理经验方法会议（EMNLP'17）论文集。2017年9月。
• Piji Li, Wai Lam, Lidong Bing, Weiwei Guo 和 Hang Li。用于压缩摘要的基于级联注意力的无监督信息蒸馏。 自然语言处理经验方法会议（EMNLP'17）论文集。2017年9月。
• Piji Li, Lidong Bing, Wai Lam。读者感知的多文档摘要：增强模型和首个数据集。 EMNLP 2017摘要新前沿研讨会（EMNLP-NewSum'17）论文集。2017年9月。
• Tan, Jiwei, Xiaojun Wan 和 Jianguo Xiao。"从神经句子摘要到标题生成：一种由粗到精的方法。" IJCAI 2017。
• Ling, Jeffrey 和 Alexander M. Rush。"用于文档摘要的由粗到精注意力模型。" EMNLP 2017 (2017年)：33。
• Ziqiang Cao, Furu Wei, Wenjie Li, Sujian Li。"忠于原文：事实感知的神经抽象摘要。" arXiv:1711.04434 (2017年)。
• Angela Fan, David Grangier, Michael Auli。"可控的抽象摘要。" arXiv:1711.05217 (2017年)。
• Liu, Linqing, Yao Lu, Min Yang, Qiang Qu, Jia Zhu 和 Hongyan Li。"用于抽象文本摘要的生成对抗网络。" arXiv预印本 arXiv:1711.09357 (2017年)。
• Narayan, Shashi, Shay B. Cohen 和 Mirella Lapata。"使用强化学习对句子进行排序以进行抽取式摘要。" arXiv预印本 arXiv:1802.08636 (2018年)。
• Asli Celikyilmaz, Antoine Bosselut, Xiaodong He, Yejin Choi。"用于抽象摘要的深度通信代理。" NAACL (2018年)。
• Chen, Wenhu, Guanlin Li, Shuo Ren, Shujie Liu, Zhirui Zhang, Mu Li 和 Ming Zhou。"神经序列预测中的生成桥接网络。" NAACL (2018年)。
• Li, Piji, Lidong Bing 和 Wai Lam。"用于抽象摘要的基于演员-评论员的训练框架。" arXiv预印本 arXiv:1803.11070 (2018年)。
• Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian。"用于长文档抽象摘要的语篇感知注意力模型"。 NAACL，2018年。
• Yuxiang Wu, Baotian Hu。"通过深度强化学习提取连贯摘要。" AAAI (2018年)。
• Jianmin Zhang, Jiwei Tan, Xiaojun Wan。"迈向基于神经网络的多文档抽象摘要。" arXiv:1804.09010 (2018年)。
• Li Wang, Junlin Yao, Yunzhe Tao, Li Zhong, Wei Liu, Qiang Du。"用于抽象文本摘要的强化主题感知卷积序列到序列模型。" IJCAI-ECAI (2018年)。
• Yen-Chun Chen, Mohit Bansal。"使用强化选择句子重写的快速抽象摘要。" arXiv:1805.11080 (2018年)。
• Song, Kaiqiang, Lin Zhao 和 Fei Liu。"用于抽象摘要的结构注入复制机制。" COLING，2018年。
• Keneshloo, Yaser, Tian Shi, Chandan K. Reddy 和 Naren Ramakrishnan。"用于序列到序列模型的深度强化学习。" arXiv预印本 arXiv:1805.09461 (2018年)。
• Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou。"顺序复制网络。" AAAI (2018年)。
• Qingyu Zhou, Nan Yang, Furu Wei, Shaohan Huang, Ming Zhou, Tiejun Zhao。"通过联合学习评分和选择句子进行神经文档摘要。" ACL (2018年)。
• Lin, Junyang, Xu Sun, Shuming Ma 和 Qi Su。"用于抽象摘要的全局编码。" arXiv预印本 arXiv:1805.03989 (2018年)。
• Khatri, Chandra, Gyanit Singh 和 Nish Parikh。"使用文档上下文向量和循环神经网络进行抽象和抽取文本摘要。" arXiv预印本 arXiv:1807.08000 (2018年)。
• Hsu, Wan-Ting, Chieh-Kai Lin, Ming-Ying Lee, Kerui Min, Jing Tang 和 Min Sun。"使用不一致性损失统一抽取式和抽象式摘要的模型。" arXiv预印本 arXiv:1805.06266 (2018年)。
• Sun, Fei, Peng Jiang, Hanxiao Sun, Changhua Pei, Wenwu Ou 和 Xiaobo Wang。"用于产品标题摘要的多源指针网络。" arXiv预印本 arXiv:1808.06885 (2018年)。
• Wojciech Kryściński, Romain Paulus, Caiming Xiong, Richard Socher。"改进文本摘要中的抽象性。" arXiv预印本 arXiv:1808.07913 (2018年)。
• Zhang, Xingxing, Mirella Lapata, Furu Wei 和 Ming Zhou。"神经潜在抽取式文档摘要。" arXiv预印本 arXiv:1808.07187 (2018年)。
• Sebastian Gehrmann, Yuntian Deng, Alexander M. Rush。"自底向上的抽象摘要。" arXiv预印本 arXiv:1808.10792 (2018年)。
• Yichen Jiang, Mohit Bansal。"封闭式训练以改进摘要编码器记忆。" arXiv预印本 arXiv:1809.04585 (2018年)。
• Kamal Al-Sabahi, Zhang Zuping, Yang Kang。"用于抽象摘要的双向注意力编码器-解码器模型和双向束搜索。" arXiv预印本 arXiv:1809.06662 (2018年)。
• Raphael Schumann。"使用长度控制变分自编码器的无监督抽象句子摘要。" arXiv预印本 arXiv:1809.05233 (2018年)。
• Krishna, Kundan 和 Balaji Vasan Srinivasan。"使用神经注意力生成面向主题的摘要。" NAACL 2018。
• Lisa Fan, Dong Yu, Lu Wang。"鲁棒的神经抽象摘要系统及对抗信息评估。" arXiv预印本 arXiv:1810.06065 (2018年)。
• Eric Chu, Peter J. Liu。"无监督神经多文档抽象摘要。" arXiv预印本 arXiv:1810.05739 (2018年)。
• Yaser Keneshloo, Naren Ramakrishnan, Chandan K. Reddy。"用于文本摘要的深度迁移强化学习。" arXiv预印本 arXiv:1810.06667 (2018年)。
• Mahnaz Koupaee, William Yang Wang。"WikiHow: 一个大规模文本摘要数据集。" arXiv预印本 arXiv:1810.09305 (2018年)。
• Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon。"用于自然语言理解和生成的统一语言模型预训练。" arXiv预印本 arXiv:1905.03197 (2019年)。

观点摘要

• Wu, Haibing, Yiwei Gu, Shangdi Sun, and Xiaodong Gu. "基于方面的观点摘要与卷积神经网络." arXiv preprint arXiv:1511.09128 (2015).
• Irsoy, Ozan, and Claire Cardie. "使用深度循环神经网络进行观点挖掘." In EMNLP, pp. 720-728. 2014.
• Piji Li, Zihao Wang, Zhaochun Ren, Lidong Bing, Wai Lam. "用于推荐的神经评分回归与抽象提示生成.". In SIGIR, 2017.

 

视频摘要

• Zhou, Kaiyang, and Yu Qiao. "用于无监督视频摘要的深度强化学习与多样性-代表性奖励." arXiv preprint arXiv:1801.00054 (2017).
• Mahasseni, Behrooz, Michael Lam, and Sinisa Todorovic. "使用对抗性LSTM网络进行无监督视频摘要." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.

阅读理解

• Hermann, Karl Moritz, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. "教机器阅读和理解." In Advances in Neural Information Processing Systems, pp. 1693-1701. 2015.
• Hill, Felix, Antoine Bordes, Sumit Chopra, and Jason Weston. "金发姑娘原则：使用显式记忆表示阅读儿童书籍." arXiv preprint arXiv:1511.02301 (2015).
• Kadlec, Rudolf, Martin Schmid, Ondrej Bajgar, and Jan Kleindienst. "使用注意力求和阅读器网络进行文本理解." arXiv preprint arXiv:1603.01547 (2016).
• Chen, Danqi, Jason Bolton, and Christopher D. Manning. "对CNN/每日邮报阅读理解任务的全面考察." arXiv preprint arXiv:1606.02858 (2016).
• Dhingra, Bhuwan, Hanxiao Liu, William W. Cohen, and Ruslan Salakhutdinov. "用于文本理解的门控注意力阅读器." arXiv preprint arXiv:1606.01549 (2016).
• Sordoni, Alessandro, Phillip Bachman, and Yoshua Bengio. "用于机器阅读的迭代交替神经注意力." arXiv preprint arXiv:1606.02245 (2016).
• Trischler, Adam, Zheng Ye, Xingdi Yuan, and Kaheer Suleman. "使用EpiReader进行自然语言理解." arXiv preprint arXiv:1606.02270 (2016).
• Yiming Cui, Zhipeng Chen, Si Wei, Shijin Wang, Ting Liu, Guoping Hu. "用于阅读理解的注意力之上的注意力神经网络." arXiv preprint arXiv:1607.04423 (2016).
• Yiming Cui, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu. "基于共识注意力的中文阅读理解神经网络." arXiv preprint arXiv:1607.02250 (2016).
• Daniel Hewlett, Alexandre Lacoste, Llion Jones, Illia Polosukhin, Andrew Fandrianto, Jay Han, Matthew Kelcey and David Berthelot. "维基阅读：一个基于维基百科的新型大规模语言理解任务." ACL (2016). pp. 1535-1545.
• Minghao Hu, Yuxing Peng, Xipeng Qiu. "用于机器理解的记忆阅读器." arXiv:1705.02798 (2017).
• Wenhui Wang, Nan Yang, Furu Wei, Baobao Chang and Ming Zhou. "R-NET：使用自匹配网络的机器阅读理解." ACL (2017).

句子建模

• Kalchbrenner, Nal, Edward Grefenstette, and Phil Blunsom. "用于句子建模的卷积神经网络." arXiv preprint arXiv:1404.2188 (2014).
• Kim, Yoon. "用于句子分类的卷积神经网络." arXiv preprint arXiv:1408.5882 (2014).
• Le, Quoc V., and Tomas Mikolov. "句子和文档的分布式表示." arXiv preprint arXiv:1405.4053 (2014).
• Yang, Zichao, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. "用于文档分类的分层注意力网络." In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

推理

• Peng, Baolin, Zhengdong Lu, Hang Li, and Kam-Fai Wong. "迈向基于神经网络的推理." arXiv preprint arXiv:1508.05508 (2015).

知识引擎

• Bordes, Antoine, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. "用于建模多关系数据的嵌入翻译." In Advances in Neural Information Processing Systems, pp. 2787-2795. 2013. TransE
• Lin, Yankai, Shiqi Shen, Zhiyuan Liu, Huanbo Luan, and Maosong Sun. "基于实例选择性注意力的神经关系抽取." ACL (2016)
• TransXXX

记忆网络

• Graves, Alex, Greg Wayne, and Ivo Danihelka. "神经图灵机." arXiv preprint arXiv:1410.5401 (2014).
• Weston, Jason, Sumit Chopra, and Antoine Bordes. "记忆网络." ICLR (2014).
• Sukhbaatar, Sainbayar, Jason Weston, and Rob Fergus. "端到端记忆网络." In Advances in neural information processing systems, pp. 2440-2448. 2015.
• Weston, Jason, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merriënboer, Armand Joulin, and Tomas Mikolov. "迈向AI完备的问答：一套先决条件的玩具任务." arXiv preprint arXiv:1502.05698 (2015).
• Bordes, Antoine, Nicolas Usunier, Sumit Chopra, and Jason Weston. "基于记忆网络的大规模简单问答." arXiv preprint arXiv:1506.02075 (2015).
• Kumar, Ankit, Ozan Irsoy, Jonathan Su, James Bradbury, Robert English, Brian Pierce, Peter Ondruska, Ishaan Gulrajani, and Richard Socher. "任意提问：用于自然语言处理的动态记忆网络." arXiv preprint arXiv:1506.07285 (2015).
• Dodge, Jesse, Andreea Gane, Xiang Zhang, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, and Jason Weston. "评估端到端对话系统学习的先决条件质量." arXiv preprint arXiv:1511.06931 (2015).
• Hill, Felix, Antoine Bordes, Sumit Chopra, and Jason Weston. "金发姑娘原则：使用显式记忆表征阅读儿童书籍." arXiv preprint arXiv:1511.02301 (2015).
• Weston, Jason. "基于对话的语言学习." arXiv preprint arXiv:1604.06045 (2016).
• Bordes, Antoine, and Jason Weston. "学习端到端目标导向对话." arXiv preprint arXiv:1605.07683 (2016).
• Chandar, Sarath, Sungjin Ahn, Hugo Larochelle, Pascal Vincent, Gerald Tesauro, and Yoshua Bengio. "分层记忆网络." arXiv preprint arXiv:1605.07427 (2016).
• Jason Weston."用于语言理解的记忆网络." ICML Tutorial 2016
• Tang, Yaohua, Fandong Meng, Zhengdong Lu, Hang Li, and Philip LH Yu. "使用外部短语记忆的神经机器翻译." arXiv preprint arXiv:1606.01792 (2016).
• Wang, Mingxuan, Zhengdong Lu, Hang Li, and Qun Liu. "用于神经机器翻译的记忆增强解码器." arXiv preprint arXiv:1606.02003 (2016).
• Xiong, Caiming, Stephen Merity, and Richard Socher. "用于视觉和文本问答的动态记忆网络." arXiv preprint arXiv:1603.01417 (2016).

神经网络结构

• Srivastava, Rupesh Kumar, Klaus Greff, and Jürgen Schmidhuber. "Highway networks." arXiv preprint arXiv:1505.00387 (2015).
• Srivastava, Rupesh K., Klaus Greff, and Jürgen Schmidhuber. "Training very deep networks." In Advances in Neural Information Processing Systems, pp. 2368-2376. 2015.
• Vinyals, Oriol, Meire Fortunato, and Navdeep Jaitly. "Pointer networks." In Advances in Neural Information Processing Systems, pp. 2692-2700. 2015.
• Rasmus, Antti, Mathias Berglund, Mikko Honkala, Harri Valpola, and Tapani Raiko. "Semi-supervised learning with ladder networks." In Advances in Neural Information Processing Systems, pp. 3546-3554. 2015.
• Bengio, Samy, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. "Scheduled sampling for sequence prediction with recurrent neural networks." In Advances in Neural Information Processing Systems, pp. 1171-1179. 2015.
• He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." arXiv preprint arXiv:1512.03385 (2015).
• He, Kaiming. "Tutorial: Deep Residual Networks: Deep Learning Gets Way Deeper." ICML 2016 tutorial.
• Courbariaux, Matthieu, and Yoshua Bengio. "Binarynet: Training deep neural networks with weights and activations constrained to+ 1 or-1." arXiv preprint arXiv:1602.02830 (2016).
• Jiatao Gu, Zhengdong Lu, Hang Li, Victor O.K. Li. "Incorporating Copying Mechanism in Sequence-to-Sequence Learning." ACL (2016)
• Gulcehre, Caglar, Sungjin Ahn, Ramesh Nallapati, Bowen Zhou, and Yoshua Bengio. "Pointing the Unknown Words." arXiv preprint arXiv:1603.08148 (2016).
• Andreas, Jacob, Marcus Rohrbach, Trevor Darrell, and Dan Klein. "Learning to compose neural networks for question answering." NAACL 2016.
• Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník, Jürgen Schmidhuber. "Recurrent Highway Networks." arXiv preprint arXiv:1607.03474 (2016).
• Zhilin Yang, Ye Yuan, Yuexin Wu, Ruslan Salakhutdinov, William W. Cohen. "Review Networks for Caption Generation." arXiv preprint arXiv:1605.07912 (2016).
• Xiang Li, Tao Qin, Jian Yang, Tie-Yan Liu. "LightRNN: Memory and Computation-Efficient Recurrent Neural Networks." arXiv preprint arXiv:1610.09893 (2016).
• Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, Hang Li. "Neural Machine Translation with Reconstruction." arXiv preprint arXiv:1611.01874 (2016).
• Yingce Xia, Di He, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, Wei-Ying Ma. "Dual Learning for Machine Translation." arXiv preprint arXiv:1611.00179 (2016).
• Bahdanau, Dzmitry, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron Courville, and Yoshua Bengio. "An actor-critic algorithm for sequence prediction." arXiv preprint arXiv:1607.07086 (2016).
• Kannan, Anjuli, and Oriol Vinyals. "Adversarial evaluation of dialogue models." arXiv preprint arXiv:1701.08198 (2017).
• Kawthekar, Prasad, Raunaq Rewari, and Suvrat Bhooshan. "Evaluating Generative Models for Text Generation."
• Li, Jiwei, Will Monroe, Tianlin Shi, Alan Ritter, and Dan Jurafsky. "Adversarial Learning for Neural Dialogue Generation." arXiv preprint arXiv:1701.06547 (2017).
• Yang, Zhen, Wei Chen, Feng Wang, and Bo Xu. "Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets." arXiv preprint arXiv:1703.04887 (2017).
• Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu. "Adversarial Neural Machine Translation." IJCAI (2017).
• Liu, Pengfei, Xipeng Qiu, and Xuanjing Huang. "Adversarial Multi-task Learning for Text Classification." arXiv preprint arXiv:1704.05742 (2017).
• Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin. "[Convolutional Sequence to Sequence Learning (https://arxiv.org/abs/1705.03122)." arXiv:1705.03122 (2017).
• Lamb, Alex M., Anirudh Goyal ALIAS PARTH GOYAL, Ying Zhang, Saizheng Zhang, Aaron C. Courville, and Yoshua Bengio. "Professor forcing: A new algorithm for training recurrent networks." In Advances In Neural Information Processing Systems, pp. 4601-4609. 2016.
• Rezende, Danilo Jimenez, Shakir Mohamed, and Daan Wierstra. "Stochastic backpropagation and approximate inference in deep generative models." arXiv preprint arXiv:1401.4082 (2014).
• Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013).
• Fabius, Otto, and Joost R. van Amersfoort. "Variational recurrent auto-encoders." arXiv preprint arXiv:1412.6581 (2014).
• Bayer, Justin, and Christian Osendorfer. "Learning stochastic recurrent networks." arXiv preprint arXiv:1411.7610 (2014).
• Bowman, Samuel R., Luke Vilnis, Oriol Vinyals, Andrew M. Dai, Rafal Jozefowicz, and Samy Bengio. "Generating sentences from a continuous space." arXiv preprint arXiv:1511.06349 (2015).
• Gregor, Karol, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, and Daan Wierstra. "DRAW: A recurrent neural network for image generation." arXiv preprint arXiv:1502.04623 (2015).
• Makhzani, Alireza, Jonathon Shlens, Navdeep Jaitly, and Ian Goodfellow. "Adversarial autoencoders." arXiv preprint arXiv:1511.05644 (2015).
• Johnson, Matthew J., David Duvenaud, Alexander B. Wiltschko, Sandeep R. Datta, and Ryan P. Adams. "Composing graphical models with neural networks for structured representations and fast inference." arXiv preprint arXiv:1603.06277 (2016).
• Doersch, Carl. "Tutorial on Variational Autoencoders." arXiv preprint arXiv:1606.05908 (2016).
• Chung, Junyoung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron C. Courville, and Yoshua Bengio. "A recurrent latent variable model for sequential data." In Advances in neural information processing systems, pp. 2980-2988. 2015.
• Eslami, S. M., Nicolas Heess, Theophane Weber, Yuval Tassa, Koray Kavukcuoglu, and Geoffrey E. Hinton. "Attend, Infer, Repeat: Fast Scene Understanding with Generative Models." arXiv preprint arXiv:1603.08575 (2016).
• Shengjia Zhao, Jiaming Song, Stefano Ermon. "InfoVAE: Information Maximizing Variational Autoencoders." arXiv:1706.02262 (2017).
• Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. "Generative adversarial nets." In Advances in Neural Information Processing Systems, pp. 2672-2680. 2014
• Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).
• Denton, Emily L., Soumith Chintala, and Rob Fergus. "Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks." In Advances in neural information processing systems, pp. 1486-1494. 2015.
• Dosovitskiy, Alexey, Jost Tobias Springenberg, and Thomas Brox. "Learning to generate chairs with convolutional neural networks." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1538-1546. 2015.
• Mathieu, Michael, Camille Couprie, and Yann LeCun. "Deep multi-scale video prediction beyond mean square error." arXiv preprint arXiv:1511.05440 (2015).
• Salimans, Tim, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. "Improved Techniques for Training GANs." arXiv preprint arXiv:1606.03498 (2016).
• Chen, Xi, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets." arXiv preprint arXiv:1606.03657 (2016).
• Im, Daniel Jiwoong, Chris Dongjoo Kim, Hui Jiang, and Roland Memisevic. "Generating images with recurrent adversarial networks." arXiv preprint arXiv:1602.05110 (2016).
• Yu, Lantao, Weinan Zhang, Jun Wang, and Yong Yu. "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." arXiv preprint arXiv:1609.05473 (2016).
• Augustus Odena, Christopher Olah, Jonathon Shlens. "Conditional Image Synthesis With Auxiliary Classifier GANs." arXiv preprint arXiv:1610.09585 (2016).
• Ian Goodfellow. "NIPS Tutorial: GANs", NIPS, 2016
• Che, Tong, Yanran Li, Ruixiang Zhang, R. Devon Hjelm, Wenjie Li, Yangqiu Song, and Yoshua Bengio. "Maximum-Likelihood Augmented Discrete Generative Adversarial Networks." arXiv preprint arXiv:1702.07983 (2017).
• Junbo (Jake) Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush, Yann LeCun. "Adversarially Regularized Autoencoders for Generating Discrete Structures." arXiv preprint arXiv:1706.04223 (2017).
• Mike Lewis Denis Yarats Yann N. Dauphin Devi Parikh Dhruv Batra . " Deal or No Deal? End-to-End Learning for Negotiation Dialogues." (2017).
• Mihaela Rosca, Balaji Lakshminarayanan, David Warde-Farley, Shakir Mohamed. "Variational Approaches for Auto-Encoding Generative Adversarial Networks." arXiv preprint arXiv:1706.04987 (2017).
• Goyal, Prasoon, Zhiting Hu, Xiaodan Liang, Chenyu Wang, and Eric Xing. "Nonparametric Variational Auto-encoders for Hierarchical Representation Learning." arXiv preprint arXiv:1703.07027 (2017).
• Sabour, Sara, Nicholas Frosst, and Geoffrey Hinton. "Dynamic Routing between Capsules." (2017).
• Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. "Attention is all you need." NIPS. 2017.

架构搜索

• Frankle, Jonathan, and Michael Carbin. "The lottery ticket hypothesis: Finding sparse, trainable neural networks." arXiv preprint arXiv:1803.03635 (2018).
• Xie, Saining, Alexander Kirillov, Ross Girshick, and Kaiming He. "Exploring Randomly Wired Neural Networks for Image Recognition." arXiv preprint arXiv:1904.01569 (2019).
• So, David R., Chen Liang, and Quoc V. Le. "The Evolved Transformer." arXiv preprint arXiv:1901.11117 (2019).
• Chenguang Wang, Mu Li, Alexander J. Smola. "Language Models with Transformers." arXiv preprint arXiv:1904.09408 (2019).

推荐系统

• Salakhutdinov, Ruslan, Andriy Mnih, and Geoffrey Hinton. "Restricted Boltzmann machines for collaborative filtering." In Proceedings of the 24th international conference on Machine learning, pp. 791-798. ACM, 2007.
• Wang, Hao, Xingjian Shi, and Dit-Yan Yeung. "Relational Stacked Denoising Autoencoder for Tag Recommendation." In AAAI, pp. 3052-3058. 2015.
• Wang, Hao, Naiyan Wang, and Dit-Yan Yeung. "Collaborative deep learning for recommender systems." In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1235-1244. ACM, 2015.
• Covington, Paul, Jay Adams, and Emre Sargin. "Deep neural networks for youtube recommendations." In Proceedings of the 10th ACM Conference on Recommender Systems, pp. 191-198. ACM, 2016.
• Devooght, Robin, and Hugues Bersini. "Collaborative Filtering with Recurrent Neural Networks." arXiv preprint arXiv:1608.07400 (2016).
• Wang, Hao, S. H. I. Xingjian, and Dit-Yan Yeung. "Collaborative recurrent autoencoder: Recommend while learning to fill in the blanks." In Advances in Neural Information Processing Systems, pp. 415-423. 2016.
• Tang, Jian, Yifan Yang, Sam Carton, Ming Zhang, and Qiaozhu Mei. "Context-aware Natural Language Generation with Recurrent Neural Networks." arXiv preprint arXiv:1611.09900 (2016).
• Zhang, Fuzheng, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma. "Collaborative Knowledge Base Embedding for Recommender Systems." KDD, 2016.
• Dong, Li, Shaohan Huang, Furu Wei, Mirella Lapata, Ming Zhou, and Ke XuΤ. "Learning to Generate Product Reviews from Attributes." EACL, 2017.
• He, Xiangnan. "Neural Collaborative Filtering." WWW, 2017
• Wu, Chao-Yuan, Amr Ahmed, Alex Beutel, Alexander J. Smola, and How Jing. "Recurrent Recommender Networks." Training 10, no. 2: 10-1.2017
• Radford, Alec, Rafal Jozefowicz, and Ilya Sutskever. "Learning to generate reviews and discovering sentiment." arXiv preprint arXiv:1704.01444 (2017).
• Piji Li, Zihao Wang, Zhaochun Ren, Lidong Bing, Wai Lam. "Neural Rating Regression with Abstractive Tips Generation for Recommendation.". In SIGIR, pp xx-xx. 2017.

网络表示学习

• 网络表示学习（NRL）/网络嵌入（NE）必读论文

音乐生成

• 使用机器学习生成音乐

计算生物学

• Awesome DeepBio by Gökçen Eraslan

围棋

• Silver, David, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser et al. "Mastering the game of Go with deep neural networks and tree search." Nature 529, no. 7587 (2016): 484-489.
• Tian, Yuandong, and Yan Zhu. "Better Computer Go Player with Neural Network and Long-term Prediction." arXiv preprint arXiv:1511.06410 (2015).

股票预测

• Xiao Ding, Yue Zhang, Ting Liu, Junwen Duan. "Deep Learning for Event-Driven Stock Prediction". IJCAI 2015.
• Si, Jianfeng, Arjun Mukherjee, Bing Liu, Sinno Jialin Pan, Qing Li, and Huayi Li. "Exploiting Social Relations and Sentiment for Stock Prediction." EMNLP 2014.
• Ding, Xiao, Yue Zhang, Ting Liu, and Junwen Duan. "Using Structured Events to Predict Stock Price Movement: An Empirical Investigation." EMNLP 2014.
• Bollen, Johan, Huina Mao, and Xiaojun Zeng. "Twitter mood predicts the stock market." Journal of Computational Science 2, no. 1 (2011): 1-8.
• Hengjian Jia. "Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction." arXiv:1603.07893. (2016)

App-DL 快速上手指南

环境准备

系统要求

• 操作系统: Linux (推荐 Ubuntu 18.04+ 或 CentOS 7+)，macOS 10.14+，Windows 10/11 (需配置 WSL 2)
• Python: 3.7 或 3.8 版本
• CUDA (GPU 用户): 10.2 或 11.x (与 PyTorch 版本匹配)

前置依赖

• Git
• pip (Python 包管理器)
• 可选: Conda 或 Miniconda (用于环境管理)

安装步骤

1. 克隆代码仓库

git clone https://github.com/lipiji/App-DL.git
cd App-DL

2. 创建 Python 虚拟环境 (推荐)

使用 Conda:

conda create -n app-dl python=3.8
conda activate app-dl

或使用 venv:

python -m venv venv
source venv/bin/activate  # Linux/macOS
# 或 venv\Scripts\activate  # Windows

3. 安装依赖包

使用国内镜像源加速下载:

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

如果缺少 requirements.txt 文件，可安装核心依赖:

pip install torch torchvision
pip install numpy pandas scikit-learn
pip install jupyter matplotlib

基本使用

1. 运行示例脚本

查看项目中的示例目录:

ls examples/

运行一个简单的深度学习示例:

python examples/basic_demo.py

2. 使用 Jupyter Notebook

启动 Jupyter 并打开教程笔记本:

jupyter notebook

在浏览器中打开 tutorials/ 目录下的 .ipynb 文件。

3. 基础模型训练

运行文本生成示例:

python train.py --config configs/text_generation.yaml

4. 测试安装

创建测试脚本 test_install.py:

import torch
import numpy as np
print("PyTorch版本:", torch.__version__)
print("CUDA可用:", torch.cuda.is_available())
print("测试完成!")

运行:

python test_install.py