Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering

Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, Xuanjing Huang


Abstract
Multi-hop reasoning requires aggregating multiple documents to answer a complex question. Existing methods usually decompose the multi-hop question into simpler single-hop questions to solve the problem for illustrating the explainable reasoning process. However, they ignore grounding on the supporting facts of each reasoning step, which tends to generate inaccurate decompositions. In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result. We employ a unified reader model for both intermediate hop reasoning and final hop inference and adopt joint optimization for more accurate and robust multi-hop reasoning. We conduct experiments on two benchmark datasets HotpotQA and 2WikiMultiHopQA. The results show that our method can effectively boost performance and also yields a better interpretable reasoning process without decomposition supervision.
Anthology ID:
2022.coling-1.142
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1655–1665
Language:
URL:
https://aclanthology.org/2022.coling-1.142
DOI:
Bibkey:
Cite (ACL):
Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, and Xuanjing Huang. 2022. Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1655–1665, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering (Wang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.142.pdf
Code
 wangsygit/stepwiseqa
Data
HotpotQA