/TRPapers

Highlight Paper about logical and text reasoning

Paper-List-on-Logical-and-Text-Reasoning

Related Work

1. Review
2. Methods
2.1 Logical Reasoning 2.2 Multi-hop Reasoning
2.3 SAT Solver 2.4 Prolog-like
2.5 Rule Learning 2.6 Relation Extraction
2.7 Fact Verification 2.8 Knowledge Distillation
3. Datasets
4. Tutorials

Plan

  1. A Review of Relational Machine Learning for Knowledge Graphs Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich paper
  2. What Can Neural Networks Reason About? ICLR 2020 spotlight Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka paper
  3. On the Capabilities and Limitations of Reasoning for Natural Language Understanding Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot, Ashish Sabharwal, Dan Roth paper
  4. Turning 30: New Ideas in Inductive Logic Programming Andrew Cropper, Sebastijan Dumančić, Stephen H. Muggleton paper
  5. Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems Laura von Rueden etc. paper
  6. From Statistical Relational to Neuro-Symbolic Artificial Intelligence Luc De Raedt, Sebastijan Dumanˇci´c , Robin Manhaeve and Giuseppe Marra paper
  1. Learning an SAT Solver from Single-Bit Supervision Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, David L. Dill 2019 ICLR paper
  2. SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver Po-Wei Wang, Priya L. Donti, Bryan Wilder, Zico Kolter 2019 ICML paper
  1. ($\partial$ILP) Learning Explanatory Rules from Noisy Data. Richard Evans, Edward Grefenstette. paper
  2. NLProlog: Reasoning with Weak Unification for Natural Language Question Answering Leon Weber, Pasquale Minervini, Ulf Leser, Tim Rocktäschel ACL 2019 paper
  3. End-to-End Differentiable Proving Tim Rocktäschel, Sebastian Riedel NIPS 2017 paper
  4. DeepProbLog: Neural Probabilistic Logic Programming Robin Manhaeve Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, Luc De Raedt NIPS 2018 paper
  1. Probabilistic Logic Neural Networks for Reasoning. Meng Qu, Jian Tang. NeurIPS 2019. paper
  2. Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension. Xinyuan Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song, Quoc V. Le ICLR 2020. paper code website note
  3. A Semantic Loss Function for Deep Learning with Symbolic Knowledge Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, Guy Van den Broeck ICML 2018. paper
  4. Neural Module Networks for Reasoning over Text Nitish Gupta1, Kevin Lin2, Dan Roth, Sameer Singh & Matt Gardner ICLR 2020 paper
  5. Neural Logic Machines Honghua Dong, Jiayuan Mao, Tian Lin, Chong Wang, Lihong Li, Denny Zhou ICLR 2019 paper
  6. Efficient Probabilistic Logic Reasoning with Graph Neural Networks Yuyu Zhang, Xinshi Chen, Yuan Yang, Arun Ramamurthy, Bo Li, Yuan Qi, Le Song ICLR 2020 paper
  7. The Logical Expressiveness of Graph Neural Network Pablo Barcelo, Egor V. Kostylev, Mikael Monet, Jorge Perez, Juan Reutter, Juan-Pablo Silva ICLR 2020 paper
  8. Transformers as Soft Reasoners over Language Peter Clark, Oyvind Tafjord, Kyle Richardson paper demo
  1. (NLIL) Learn to Explain Efficiently via Neural Logic Inductive Learning Yuan Yang, Le Song ICLR 2020 paper
  2. Scalable Rule Learning via Learning Representation Pouya Ghiasnezhad Omran, Kewen Wang, Zhe Wang IJCAI 2018 paper
  3. Generating Logical Forms from Graph Representations of Text and Entities Peter Shaw, Philip Massey, Angelica Chen, Francesco Piccinno, Yasemin Altun ACL 2019 paper
  4. (NeuralLP) Differentiable Learning of Logical Rules for Knowledge Base Reasoning Fan Yang, Zhilin Yang, William W. Cohen NIPS 2017 paper
  5. (roundILP) Learning Explanatory Rules from Noisy Data Richard Evans, Edward Grefenstette JAIR 2017 paper
  6. Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning Wen Zhang, Bibek Paudel, Liang Wang, Jiaoyan Chen, Hai Zhu, Wei Zhang, Abraham Bernstein, Huajun Chen paper
  7. Differentiable Reasoning on Large Knowledge Bases and Natural Language Pasquale Minervini, Matko Bošnjak, Tim Rocktäschel, Sebastian Riedel, Edward Grefenstette paper
  8. Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and Reasoning Arindam Mitra, Chitta Baral AAAI 2016 paper
  1. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, Caiming Xiong. ICLR 2020 paper code
  2. Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention Chen Zhao, Chenyan Xiong, Corby Rosset, Xia Song, Paul Bennett, Saurabh Tiwary. ICLR 2020 paper
  3. Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs. Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, Bowen Zhou. ACL 2019. paper code
  4. Cognitive Graph for Multi-Hop Reading Comprehension at Scale Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang. ACL 2019 paper
  5. Dynamically Fused Graph Network for Multi-hop Reasoning. Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu ACL 2019. paper
  6. A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning. Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li. EMNLP 2019. paper code
  7. Multi-range Reasoning for Machine Comprehension. Yi Tay, Luu Anh Tuan, and Siu Cheung Hui paper
  8. Differentiable Reasoning Over A Virtual Knowledge Base Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov1, William W. Cohen. ICLR 2020 paper
  9. Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base William W. Cohen, Haitian Sun, R. Alex Hofer, Matthew Siegler ICLR 2020 paper
  10. Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi paper
  1. (OpenIE) Leveraging Linguistic Structure For Open Domain Information Extraction Gabor Angeli, Melvin Johnson Premkumar, Christopher D. Manning paper
  1. Deep Neural Networks with Massive Learned Knowledge Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric Xing EMNLP 2016 paper

  2. Deep Generative Models with Learnable Knowledge Constraints Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Xiaodan Liang, Lianhui Qin, Haoye Dong, Eric Xing NIPS 2018 paper

  3. Toward Controlled Generation of Text Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, Eric P. Xing ICML 2017 paper

  4. Harnessing Deep Neural Networks with Logic Rules Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy, Eric Xing 2016 ACL paper

  1. GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun. ACL 2019 paper
  1. DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. NAACL 2019. paper data website
  2. (bAbI)Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks Jason Weston, Antoine Bordes, Sumit Chopra, Alexander M. Rush, Bart van Merriënboer, Armand Joulin, Tomas Mikolov ICLR 2016 paper website
  3. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, Christopher D. Manning. EMNLP 2018 paper website
  4. ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning. Weihao Yu, Zihang Jiang, Yanfei Dong, Jiashi Feng. ICLR 2020. paper code website note
  5. RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension Naoya Inoue, Pontus Stenetorp, Kentaro Inui paper
  6. Counterfactual Story Reasoning and Generation Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi EMNLP 2019 paper
  7. Abductive Commonsense Reasoning Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Scott Wen-tau Yih, Yejin Choi paper website
  8. PIQA: Reasoning about Physical Commonsense in Natural Language. Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, Yejin Choi. AAAI 2020 paper
  9. CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text. Koustuv Sinha, Shagun Sodhani, Jin Dong, Joelle Pineau, William L. Hamilton EMNLP 2019 paper code website
  10. COSMOS QA: Machine Reading Comprehension with Contextual Commonsense Reasoning Lifu Huang, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi EMNLP 2019 paper website
  1. Mining Knowledge Graphs from Text Jay Pujara, Sameer Singh website
  2. Logic and Proof Jeremy Avigad, Robert Y. Lewis, and Floris van Doorn website
  3. Graph Neural Networks for Natural Language Processing Shikhar Vashishth, Y. Naganand, Partha Talukdar EMNLP 2019 Tutorial slides