[go: up one dir, main page]

Universal Information Extraction with Meta-Pretrained Self-Retrieval

Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang


Abstract
Universal Information Extraction (Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to struggle when there exist complex information structures to be extracted. Retrieving knowledge from external knowledge bases may help models to overcome this problem but it is impossible to construct a knowledge base suitable for various IE tasks. Inspired by the fact that large amount of knowledge are stored in the pretrained language models (PLM) and can be retrieved explicitly, in this paper, we propose MetaRetriever to retrieve task-specific knowledge from PLMs to enhance universal IE. As different IE tasks need different knowledge, we further propose a Meta-Pretraining Algorithm which allows MetaRetriever to quicktly achieve maximum task-specific retrieval performance when fine-tuning on downstream IE tasks. Experimental results show that MetaRetriever achieves the new state-of-the-art on 4 IE tasks, 12 datasets under fully-supervised, low-resource and few-shot scenarios.
Anthology ID:
2023.findings-acl.251
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4084–4100
Language:
URL:
https://aclanthology.org/2023.findings-acl.251
DOI:
10.18653/v1/2023.findings-acl.251
Bibkey:
Cite (ACL):
Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, and Bin Wang. 2023. Universal Information Extraction with Meta-Pretrained Self-Retrieval. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4084–4100, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Universal Information Extraction with Meta-Pretrained Self-Retrieval (Cong et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.251.pdf