Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension (2306.12069v1)

Published 21 Jun 2023 in cs.CL and cs.LG

Abstract: Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical relations exist at different granularity levels. However, most existing methods of logical reasoning individually focus on either entity-aware or discourse-based information but ignore the hierarchical relations that may even have mutual effects. In this paper, we propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning, to provide a more fine-grained relation extraction. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism to improve the interpretation of MRC systems. Experimental results on logical reasoning QA datasets (ReClor and LogiQA) and natural language inference datasets (SNLI and ANLI) show the effectiveness and generalization of our method, and in-depth analysis verifies its capability to understand complex logical relations.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. Neurquri: Neural question requirement inspector for answerability prediction in machine reading comprehension. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  2. Neural-symbolic learning and reasoning: A survey and interpretation. arXiv preprint arXiv:1711.03902.
  3. Abductive commonsense reasoning. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  4. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computational Linguistics.
  5. Multi-hop question answering via reasoning chains. arXiv preprint arXiv:1910.02610.
  6. Neural symbolic reader: Scalable integration of distributed and symbolic representations for reading comprehension. In International Conference on Learning Representations.
  7. QuAC: Question answering in context. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2174–2184, Brussels, Belgium. Association for Computational Linguistics.
  8. MuTual: A dataset for multi-turn dialogue reasoning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1406–1416, Online. Association for Computational Linguistics.
  9. Ernest Davis and Gary Marcus. 2015. Commonsense reasoning and commonsense knowledge in artificial intelligence. Communications of the ACM, 58(9):92–103.
  10. Cognitive graph for multi-hop reading comprehension at scale. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2694–2703, Florence, Italy. Association for Computational Linguistics.
  11. Hierarchical graph network for multi-hop question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8823–8838, Online. Association for Computational Linguistics.
  12. Discern: Discourse-aware entailment reasoning network for conversational machine reading. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2439–2449, Online. Association for Computational Linguistics.
  13. Neural-symbolic learning and reasoning: contributions and challenges. In 2015 AAAI Spring Symposium Series.
  14. Teaching machines to read and comprehend. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 1693–1701.
  15. Cosmos QA: Machine reading comprehension with contextual commonsense reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2391–2401, Hong Kong, China. Association for Computational Linguistics.
  16. DAGN: Discourse-aware graph network for logical reasoning. In NAACL.
  17. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  18. RACE: Large-scale ReAding comprehension dataset from examinations. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 785–794, Copenhagen, Denmark. Association for Computational Linguistics.
  19. Segbot: A generic neural text segmentation model with pointer network. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden, pages 4166–4172. ijcai.org.
  20. Logiqa: A challenge dataset for machine reading comprehension with logical reasoning. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pages 3622–3628. ijcai.org.
  21. Adversarial training for large neural language models. arXiv preprint arXiv:2004.08994.
  22. Adversarial NLI: A new benchmark for natural language understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.
  23. Dialogue graph modeling for conversational machine reading. In The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021).
  24. Fact-driven logical reasoning. arXiv preprint arXiv:2105.10334.
  25. Dynamically fused graph network for multi-hop reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6140–6150, Florence, Italy. Association for Computational Linguistics.
  26. Know what you don’t know: Unanswerable questions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 784–789, Melbourne, Australia. Association for Computational Linguistics.
  27. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics.
  28. CoQA: A conversational question answering challenge. Transactions of the Association for Computational Linguistics, 7:249–266.
  29. Hongyu Ren and Jure Leskovec. 2020. Beta embeddings for multi-hop logical reasoning in knowledge graphs. Advances in Neural Information Processing Systems, 33.
  30. Benchmarking machine reading comprehension: A psychological perspective. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1592–1612.
  31. CommonsenseQA: A question answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4149–4158, Minneapolis, Minnesota. Association for Computational Linguistics.
  32. Infobert: Improving robustness of language models from an information theoretic perspective. arXiv preprint arXiv:2010.02329.
  33. Logic-driven context extension and data augmentation for logical reasoning of text. arXiv preprint arXiv:2105.03659.
  34. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics.
  35. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–2380, Brussels, Belgium. Association for Computational Linguistics.
  36. Reclor: A reading comprehension dataset requiring logical reasoning. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  37. Sg-net: Syntax-guided machine reading comprehension. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 9636–9643. AAAI Press.
  38. Retrospective reader for machine reading comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16):14506–14514.
  39. Machine reading comprehension: The role of contextualized language models and beyond. arXiv preprint arXiv:2005.06249.
  40. AR-LSAT: Investigating Analytical Reasoning of Text. arXiv e-prints, page arXiv:2104.06598.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Jialin Chen (39 papers)
  2. Zhuosheng Zhang (125 papers)
  3. Hai Zhao (227 papers)
Citations (4)
View on Semantic Scholar