Pre-training to Match for Unified Low-shot Relation Extraction

Fangchao Liu, Hongyu Lin, Xianpei Han, Boxi Cao, Le Sun


Abstract
Low-shot relation extraction (RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application. Few-shot and zero-shot RE are two representative low-shot RE tasks, which seem to be with similar target but require totally different underlying abilities. In this paper, we propose Multi-Choice Matching Networks to unify low-shot relation extraction. To fill in the gap between zero-shot and few-shot RE, we propose the triplet-paraphrase meta-training, which leverages triplet paraphrase to pre-train zero-shot label matching ability and uses meta-learning paradigm to learn few-shot instance summarizing ability. Experimental results on three different low-shot RE tasks show that the proposed method outperforms strong baselines by a large margin, and achieve the best performance on few-shot RE leaderboard.
Anthology ID:
2022.acl-long.397
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5785–5795
Language:
URL:
https://aclanthology.org/2022.acl-long.397
DOI:
10.18653/v1/2022.acl-long.397
Bibkey:
Cite (ACL):
Fangchao Liu, Hongyu Lin, Xianpei Han, Boxi Cao, and Le Sun. 2022. Pre-training to Match for Unified Low-shot Relation Extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5785–5795, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Pre-training to Match for Unified Low-shot Relation Extraction (Liu et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.397.pdf
Code
 fc-liu/mcmn
Data
FewRel