Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

Yichen Jiang, Nitish Joshi, Yen-Chun Chen, Mohit Bansal


Abstract
Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage’s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system’s ability to perform interpretable and accurate reasoning.
Anthology ID:
P19-1261
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2714–2725
Language:
URL:
https://aclanthology.org/P19-1261
DOI:
10.18653/v1/P19-1261
Bibkey:
Cite (ACL):
Yichen Jiang, Nitish Joshi, Yen-Chun Chen, and Mohit Bansal. 2019. Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2714–2725, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension (Jiang et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1261.pdf
Video:
 https://vimeo.com/384968126
Code
 jiangycTarheel/EPAr
Data
MedHopWikiHop