Skip to content

Latest commit

 

History

History
347 lines (177 loc) · 14.8 KB

v1.md

File metadata and controls

347 lines (177 loc) · 14.8 KB
Raw

Papers on Knowledge-based Machine Reading Comprehension.

A list of recent papers about Knowledge-based Machine Reading Comprehension (KMRC).

Contributed by Luxi Xing and Yuqiang Xie.

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China.

Update on Oct. 23, 2019.

(the current version only contains the works published on the conferences or journals, we will continuously update this list.)

Content

  1. Survey
  2. Cloze Style Tasks
  3. Span Extraction Tasks
  4. Multiple Choice Tasks
  5. Generation Tasks
  6. Datasets

Note: papers about KBQA will be not included in this list.

Survey Papers

  1. Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches. 2019. [paper / note]

    Authors: Shane Storks, Qianzi Gao, Joyce Y. Chai

  2. Neural Machine Reading Comprehension: Methods and Trends. 2019. [paper]

    Authors: Shanshan Liu, Xin Zhang, Sheng Zhang, Hui Wang, Weiming Zhang

  3. Machine Reading Comprehension: a Literature Review. 2019. [paper]

    Authors: Xin Zhang, An Yang, Sujian Li, Yizhong Wang

Cloze Style Tasks

  1. World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions. EMNLP,2017.

    Authors: Teng Long, Emmanuel Bengio, Ryan Lowe Jackie Chi Kit Cheung, Doina Precup

    Links: paper

    Tasks: Rare Entity Prediction;

  2. Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension. ACL,2017.

    Authors: Hongyu Lin, Le Sun, Xianpei Han

    Links: paper

    Tasks: SCT;

  3. Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge. ACL,2018.

    Authors: Todor Mihaylov, Anette Frank

    Links: paper / code / note

    Tasks: Common Nouns;

  4. A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task. COLING,2018.

    Authors: Qian Li, Ziwei Li, Jin-Mao Wei, Yanhui Gu, Adam Jatowt, Zhenglu Yang

    Links: paper

    Tasks: SCT;

  5. Incorporating Structured Commonsense Knowledge in Story Completion. AAAI,2018.

    Authors: Jiaao Chen, Jianshu Chen, Zhou Yu

    Links: paper

    Tasks: SCT;

  6. Story Ending Prediction by Transferable BERT. IJCAI,2019.

    Authors: Zhongyang Li, Xiao Ding, Ting Liu

    Links: paper

    Tasks: SCT;

Span Extraction Tasks

  1. Dynamic Integration of Background Knowledge in Neural NLU Systems. arxiv,2018.

    Authors: Dirk Weissenborn, Tomas Kocisky, Chris Dyer

    Links: paper

    Tasks: SQuAD; TriviaQA;

  2. Explicit Utilization of General Knowledge in Machine Reading Comprehension. ACL,2019.

    Authors: Chao Wang, Hui Jiang

    Links: paper / note

    Tasks: SQuAD;

  3. Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension. ACL,2019.

    Authors: An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

    Links: paper / note

    Tasks: SQuAD; ReCoRD;

Multiple Choice Tasks

  1. Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension. SemEval,2018.

    Author: Liang Wang, Meng Sun, Wei Zhao, Kewei Shen, Jingming Liu

    Links: paper / code

    Tasks: SemEval-2018 Task 11;

  2. Improving Question Answering by Commonsense-Based Pre-Training. AAAI,2019.

    Authors: Wanjun Zhong, Duyu Tang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

    Links: paper

    Tasks: ARC; OpenBookQA; SemEval-2018 Task 11;

  3. Improving Machine Reading Comprehension with General Reading Strategies. NAACL,2019.

    Authors: Kai Sun, Dian Yu, Dong Yu, Claire Cardie

    Links: paper / code

    Tasks: ARC; OpenBookQA; MCTest; SemEval-2018 Task 11; SCT; MultiRC;

  4. Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs. NAACL,2019.

    Authors: Debjit Paul, Anette Frank

    Links: paper / code

    Tasks: story commonsense;

  5. Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning. CIKM,2019.

    Author: Jiangnan Xia, Chen Wu, Ming Yan

    Links: paper

    Tasks: SemEval-2018 Task 11 / SCT;

  6. Explain Yourself! Leveraging Language Models for Commonsense Reasoning. ACL,2019.

    Authors: Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, Richard Socher

    Links: paper / code / note

    Tasks: CommonsenseQA;

  7. Careful Selection of Knowledge to solve Open Book Question Answering. ACL,2019.

    Authors: Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra, Chitta Baral

    Links: paper

    Tasks: OpenBookQA;

  8. Improving Question Answering with External Knowledge. EMNLP-MRQA,2019.

    Authors: Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu

    Links: paper / note

    Tasks: ARC; OpenBookQA;

  9. KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning. EMNLP,2019.

    Authors: Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren

    Links: paper / code / note

    Tasks: CommonsenseQA;

  10. What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering. EMNLP,2019.

    Authors: Tushar Khot, Ashish Sabharwal, Peter Clark

    Links: paper/ note

    Tasks: OpenBookQA;

  11. BIG MOOD: Relating Transformers to Explicit Commonsense Knowledge. EMNLP-COIN,2019.

    Authors: Jeff Da

    Links: paper

    Tasks: MCScripts-v2;

Generation Tasks

Also known as Free-form Answer Tasks

  1. Commonsense for Generative Multi-Hop Question Answering Tasks. EMNLP,2018.

    Authors: Lisa Bauer, Yicheng Wang, Mohit Bansal

    Links: paper / code / note

    Tasks: NarrativeQA; QAngaroo-WikiHop;

  2. COMET: Commonsense Transformers for Automatic Knowledge Graph Construction. ACL,2019.

    Authors: Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi

    Links: paper / code / note

    Tasks: Atomic;

  3. Incorporating External Knowledge into Machine Reading for Generative Question Answering. EMNLP,2019.

    Authors: Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

    Links: paper / note

    Tasks: MS MARCO;

Benchmark Datasets

  1. [COPA] Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning. AAAI,2011. [paper / data]

    Authors: Melissa Roemmele, Cosmin Adrian Bejan, Andrew S. Gordon

    • Type: Multiple-Choice;

  2. [WSC] The Winograd Schema Challenge. AAAI,2011. [paper /data]

    Authors: Hector J. Levesque, Ernest Davis, Leora Morgenstern

    • Type: Multiple-Choice;

  3. [ROCStories; SCT] A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories. NAACL,2016. [paper / data]

    Authors: Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen

    • Type: Cloze;

  4. [NarrativeQA] The NarrativeQA Reading Comprehension Challenge. TACL,2018. [paper / data]

    Authors: Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gábor Melis, Edward Grefenstette

    • Type: Generation;

  5. [SemEval-2018 Task 11] MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge. LERC,2018. [paper / data]

    Authors: Simon Ostermann, Ashutosh Modi, Michael Roth, Stefan Thater, Manfred Pinkal

    • Type: Multiple-Choice;

  6. [story-commonsense] Modeling Naive Psychology of Characters in Simple Commonsense Stories. ACL,2018. [paper / data]

    Authors: Hannah Rashkin, Antoine Bosselut, Maarten Sap, Kevin Knight, Yejin Choi

    • Type: Multiple-Choice;

  7. Event2Mind: Commonsense Inference on Events, Intents, and Reactions. ACL,2018. [paper / data]

    Authors: Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A. Smith, Yejin Choi

    • Types: Generation;

  8. ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI,2019. [paper / data]

    Authors: Maarten Sap, Ronan LeBras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, Yejin Choi

    • Types: Generation;

  9. [ARC] Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. 2018. [paper / data]

    Authors: Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord

    • Type: Multiple-Choice;

  10. [OpenBookQA] Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering. EMNLP,2018. [paper / data]

    Authors: Todor Mihaylov, Peter Clark, Tushar Khot, Ashish Sabharwal

    • Type: Multiple-Choice;

  11. ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension. 2018. [paper / data]

    Authors: Sheng Zhang, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Kevin Duh, Benjamin Van Durme

    • Type: Cloze;

  12. CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge. NAACL,2019. [paper / data]

    Authors: Alon Talmor, Jonathan Herzig, Nicholas Lourie, Jonathan Berant

    • Type: Multiple-Choice;

  13. ChID: A Large-scale Chinese IDiom Dataset for Cloze Test. ACL,2019. [paper / data]

    Authors: Chujie Zheng, Minlie Huang, Aixin Sun

    • Type: Cloze;

  14. [sense-making] Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation. ACL,2019. [paper / data]

    Authors: Cunxiang Wang, Shuailong Liang, Yue Zhang, Xiaonan Li, Tian Gao

    • Type: Multiple-Choice;

  15. HellaSwag: Can a Machine Really Finish Your Sentence? ACL,2019. [paper / data]

    Authors: Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, Yejin Choi

    • Type: Multiple-Choice;

  16. SocialIQA: Commonsense Reasoning about Social Interactions. EMNLP,2019. [paper / data]

    Authors: Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, Yejin Choi

    • Type: Multiple-Choice;

  17. [ANLI] Abductive Commonsense Reasoning. 2019. [paper / data]

    Authors: Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Scott Wen-tau Yih, Yejin Choi

    • Type: Multiple-Choice;

  18. Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning. EMNLP,2019. [paper / data]

    Authors: Lifu Huang, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

    • Type: Multiple-Choice;

Note: Only consider the benchmark datasets/tasks which require knowledge to complete.

Other Paper List About MRC

thunlp/RCPapers