Abstract
We target on the document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction (RE) at once, and gets evaluated in an entity-centric way. Especially, we address the two-way interaction between COREF and RE that has not been the focus by previous work, and propose to introduce explicit interaction namely Graph Compatibility (GC) that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. Our experiments are conducted on DocRED and DWIE; in addition to GC, we implement and compare different multi-task settings commonly adopted in previous work, including pipeline, shared encoders, graph propagation, to examine the effectiveness of different interactions. The result shows that GC achieves the best performance by up to 2.3/5.1 F1 improvement over the baseline.- Anthology ID:
- 2022.naacl-main.395
- 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:
- 5409–5416
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.395
- DOI:
- 10.18653/v1/2022.naacl-main.395
- Cite (ACL):
- Liyan Xu and Jinho Choi. 2022. Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5409–5416, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction (Xu & Choi, NAACL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.naacl-main.395.pdf
- Data
- DWIE, DocRED