Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering

Jianmo Ni, Chenguang Zhu, Weizhu Chen, Julian McAuley


Abstract
Open-domain question answering remains a challenging task as it requires models that are capable of understanding questions and answers, collecting useful information, and reasoning over evidence. Previous work typically formulates this task as a reading comprehension or entailment problem given evidence retrieved from search engines. However, existing techniques struggle to retrieve indirectly related evidence when no directly related evidence is provided, especially for complex questions where it is hard to parse precisely what the question asks. In this paper we propose a retriever-reader model that learns to attend on essential terms during the question answering process. We build (1) an essential term selector which first identifies the most important words in a question, then reformulates the query and searches for related evidence; and (2) an enhanced reader that distinguishes between essential terms and distracting words to predict the answer. We evaluate our model on multiple open-domain QA datasets, notably achieving the level of the state-of-the-art on the AI2 Reasoning Challenge (ARC) dataset.
Anthology ID:
N19-1030
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
335–344
Language:
URL:
https://aclanthology.org/N19-1030
DOI:
10.18653/v1/N19-1030
Bibkey:
Cite (ACL):
Jianmo Ni, Chenguang Zhu, Weizhu Chen, and Julian McAuley. 2019. Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 335–344, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering (Ni et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/N19-1030.pdf
Code
 nijianmo/arc-etrr-code +  additional community code
Data
ARC (AI2 Reasoning Challenge)RACETriviaQA