Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering

Jpliu@wtu.edu.cn Jpliu@wtu.edu.cn, Shijie Mei, Xinrong Hu, Xun Yao, Jack Yang, Yi Guo


Abstract
Given a context knowledge base (KB) and a corresponding question, the Knowledge Base Question Answering task aims to retrieve correct answer entities from this KB. Despite sophisticated retrieval algorithms, the impact of the low-resource (incomplete) KB is not fully exploited, where contributing components (. key entities and/or relations) may be absent for question answering. To effectively address this problem, we propose a contrastive regularization based method, which is motivated by the learn-by-analogy capability from human readers. Specifically, the proposed work includes two major modules: the knowledge extension and sMoCo module. The former aims at exploiting the latent knowledge from the context KB and generating auxiliary information in the form of question-answer pairs. The later module utilizes those additional pairs and applies the contrastive regularization to learn informative representations, that making hard positive pairs attracted and hard negative pairs separated. Empirically, we achieved the state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.
Anthology ID:
2022.findings-naacl.82
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1085–1094
Language:
URL:
https://aclanthology.org/2022.findings-naacl.82
DOI:
10.18653/v1/2022.findings-naacl.82
Bibkey:
Cite (ACL):
Jpliu@wtu.edu.cn Jpliu@wtu.edu.cn, Shijie Mei, Xinrong Hu, Xun Yao, Jack Yang, and Yi Guo. 2022. Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1085–1094, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering (Jpliu@wtu.edu.cn et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.82.pdf
Video:
 https://aclanthology.org/2022.findings-naacl.82.mp4
Code
 jakeymei/smoco
Data
WebQuestionsSP