Abstract
In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multipleevents may lie in one document (multi-event issue). In this paper, we argue that the relation information of event arguments is of greatsignificance for addressing the above two issues, and propose a new DEE framework which can model the relation dependencies, calledRelation-augmented Document-level Event Extraction (ReDEE). More specifically, this framework features a novel and tailored transformer,named as Relation-augmented Attention Transformer (RAAT). RAAT is scalable to capture multi-scale and multi-amount argument relations. To further leverage relation information, we introduce a separate event relation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance. Extensive experiments demonstrate the effectiveness of the proposed method, which can achieve state-of-the-art performance on two public datasets. Our code is available at https://github.com/TencentYoutuResearch/RAAT.- Anthology ID:
- 2022.naacl-main.367
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4985–4997
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.367
- DOI:
- 10.18653/v1/2022.naacl-main.367
- Cite (ACL):
- Yuan Liang, Zhuoxuan Jiang, Di Yin, and Bo Ren. 2022. RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4985–4997, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction (Liang et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.naacl-main.367.pdf
- Code
- TencentYoutuResearch/EventExtraction-RAAT
- Data
- ChFinAnn