Easy-to-Hard Learning for Information Extraction
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractInformation 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-tohard 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. Our code is available at https://github.com/DAMO-NLP-SG/IE-E2H.
All Author(s) ListChang Gao, Wenxuan Zhang, Wai Lam, Lidong Bing
Name of ConferenceThe 61st Annual Meeting of the Association for Computational Linguistics (ACL)
Start Date of Conference09/07/2023
End Date of Conference14/07/2023
Place of ConferenceToronto
Country/Region of ConferenceCanada
Proceedings TitleFindings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)
Year2023
Month7
Pages11913 - 11930
LanguagesEnglish-United States

Last updated on 2023-14-09 at 09:52