Easy-to-Hard Learning for Information Extraction

Chang Gao, Wenxuan Zhang, Wai Lam, Lidong Bing


Abstract
Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts. While most existing work addresses a particular IE task, universally modeling various IE tasks with one model has achieved great success recently. Despite their success, they employ a one-stage learning strategy, i.e., directly learning to extract the target structure given the input text, which contradicts the human learning process. In this paper, we propose a unified easy-to-hard learning framework consisting of three stages, i.e., the easy stage, the hard stage, and the main stage, for IE by mimicking the human learning process. By breaking down the learning process into multiple stages, our framework facilitates the model to acquire general IE task knowledge and improve its generalization ability. Extensive experiments across four IE tasks demonstrate the effectiveness of our framework. We achieve new state-of-the-art results on 13 out of 17 datasets.
Anthology ID:
2023.findings-acl.754
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11913–11930
Language:
URL:
https://aclanthology.org/2023.findings-acl.754
DOI:
Bibkey:
Cite (ACL):
Chang Gao, Wenxuan Zhang, Wai Lam, and Lidong Bing. 2023. Easy-to-Hard Learning for Information Extraction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11913–11930, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Easy-to-Hard Learning for Information Extraction (Gao et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2023.findings-acl.754.pdf