Skip to content

Latest commit

聽

History

History
75 lines (53 loc) 路 5.21 KB

papers-multi-hop.md

File metadata and controls

75 lines (53 loc) 路 5.21 KB
Raw

Papers on Multi-Hop Machine Reading Comprehension

A list of recent papers about Multi-Hop Machine Reading Comprehension.

Contributed by Luxi Xing, Yuqiang Xie and Wei Peng.

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

Update on Aug. 6, 2020.

(the current version only contains the works published on the conferences or journals.)

Content

  1. Datasets
  2. HotpotQA
  3. Wikihop

Benchmark Datasets

  1. [WikiHop] Constructing Datasets for Multi-hop Reading Comprehension Across Documents. TACL,2018. [paper / data]

    Authors: Johannes Welbl, Pontus Stenetorp, Sebastian Riedel

  2. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. EMNLP,2018. [paper / data]

    Authors: Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, Christopher D. Manning

  3. R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason. ACL,2020. [paper / data / note]

    Authors: Naoya Inoue, Pontus Stenetorp, Kentaro Inui

HotpotQA

  1. Cognitive Graph for Multi-Hop Reading Comprehension at Scale. ACL,2019. paper.

  2. Dynamically Fused Graph Network for Multi-hop Reasoning. ACL,2019. paper.

  3. Answering while Summarizing: Multi-task Learning for Multi-Hop QA with Evidence Extraction. ACL,2019. paper.

  4. Compositional Questions Do Not Necessitate Multi-hop Reasoning. ACL,2019. paper.

  5. Multi-hop Reading Comprehension through Question Decomposition and Rescoring. ACL,2019. paper.

  6. Answering Complex Open-domain Questions Through Iterative Query Generation. EMNLP,2019. paper.

  7. Revealing the Importance of Semantic Retrieval for Machine Reading at Scale. EMNLP,2019. paper.

  8. Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks. EMNLP,2019,TextGraphs-13. paper.

  9. Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning. EMNLP,2019. paper.

  10. Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering. EMNLP,2019,MRQA. paper.

  11. Multi-Hop Paragraph Retrieval for Open-Domain Question Answering. ICLR,2019.

  12. Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA. ACL,2019.

  13. Multi-hop Reading Comprehension through Question Decomposition and Rescoring. ACL,2019.

  14. Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering. MRQA,2019.

  15. Answering Complex Open-domain Questions Through Iterative Query Generation. EMNLP,2019.

  16. Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents. 2019.

  17. Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks. 2019.

  18. Multi-hop Question Answering via Reasoning Chains. 2019.

  19. A Road-map Towards Explainable Question Answering A Solution for Information Pollution. 2019.

  20. Hierarchical Graph Network for Multi-hop Question Answering. 2019.

  21. Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network. 2019.

  22. Neural Module Networks for Reasoning over Text. 2019.

  23. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering. 2019.

Wikihop

  1. Neural Models for Reasoning over Multiple Mentions using Coreference. NAACL,2018,short. paper
  2. Exploring graph-structured passage representation for multihop reading comprehension with graph neural networks. 2018.
  3. Exploiting explicit paths for multihop reading comprehension. 2018.
  4. BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering. NAACL,2019.
  5. Question Answering by Reasoning Across Documents with Graph Convolutional Networks. NAACL,2019.
  6. Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs. ACL,2019.
  7. Coarse-Grain Fine-Grain Coattention Network for Multi-Evidence Question Answering. ICLR,2019.
  8. Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension. ACL,2019.