Dynamically Fused Graph Network for Multi-hop Reasoning
Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu
Abstract
Text-based question answering (TBQA) has been studied extensively in recent years. Most existing approaches focus on finding the answer to a question within a single paragraph. However, many difficult questions require multiple supporting evidence from scattered text among two or more documents. In this paper, we propose Dynamically Fused Graph Network (DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them. Inspired by human’s step-by-step reasoning behavior, DFGN includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores along the entity graph dynamically built from the text, and gradually finds relevant supporting entities from the given documents. We evaluate DFGN on HotpotQA, a public TBQA dataset requiring multi-hop reasoning. DFGN achieves competitive results on the public board. Furthermore, our analysis shows DFGN produces interpretable reasoning chains.- Anthology ID:
- P19-1617
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6140–6150
- Language:
- URL:
- https://aclanthology.org/P19-1617
- DOI:
- 10.18653/v1/P19-1617
- Cite (ACL):
- Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, and Yong Yu. 2019. 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.
- Cite (Informal):
- Dynamically Fused Graph Network for Multi-hop Reasoning (Qiu et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/P19-1617.pdf
- Code
- woshiyyya/DFGN-pytorch
- Data
- ComplexWebQuestions, HotpotQA, SQuAD, WikiHop