Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, Andrew McCallum


Abstract
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find multiple supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to ‘hop’ to other relevant evidence. In a setting, with more than 5 million Wikipedia paragraphs, our approach leads to significant boost in retrieval performance. The retrieved evidence also increased the performance of an existing QA model (without any training) on the benchmark by 10.59 F1.
Anthology ID:
D19-5816
Volume:
Proceedings of the 2nd Workshop on Machine Reading for Question Answering
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
113–118
Language:
URL:
https://aclanthology.org/D19-5816
DOI:
10.18653/v1/D19-5816
Bibkey:
Cite (ACL):
Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, and Andrew McCallum. 2019. Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 113–118, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (Das et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5816.pdf