Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, Bowen Zhou


Abstract
Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop RC problem. We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph. The advantage of HDE graph is that it contains different granularity levels of information including candidates, documents and entities in specific document contexts. Our proposed model can do reasoning over the HDE graph with nodes representation initialized with co-attention and self-attention based context encoders. We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. Evaluated on the blind test set of the Qangaroo WikiHop data set, our HDE graph based single model delivers competitive result, and the ensemble model achieves the state-of-the-art performance.
Anthology ID:
P19-1260
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:
2704–2713
Language:
URL:
https://www.aclweb.org/anthology/P19-1260
DOI:
10.18653/v1/P19-1260
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P19-1260.pdf
Supplementary:
 P19-1260.Supplementary.pdf
Video:
 https://vimeo.com/384732193