What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

Tushar Khot, Ashish Sabharwal, Peter Clark


Abstract
Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is provided with each question. The model must retrieve and use additional knowledge to correctly answer the question. To tackle this challenge, we develop a novel approach that explicitly identifies the knowledge gap between a key span in the provided knowledge and the answer choices. The model, GapQA, learns to fill this gap by determining the relationship between the span and an answer choice, based on retrieved knowledge targeting this gap. We propose jointly training a model to simultaneously fill this knowledge gap and compose it with the provided partial knowledge. On the OpenBookQA dataset, given partial knowledge, explicitly identifying what’s missing substantially outperforms previous approaches.
Anthology ID:
D19-1281
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2814–2828
Language:
URL:
https://aclanthology.org/D19-1281
DOI:
10.18653/v1/D19-1281
Bibkey:
Cite (ACL):
Tushar Khot, Ashish Sabharwal, and Peter Clark. 2019. What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2814–2828, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering (Khot et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1281.pdf
Attachment:
 D19-1281.Attachment.pdf
Code
 allenai/missing-fact
Data
ConceptNetOpenBookQASQuAD