Entity, Relation, and Event Extraction with Contextualized Span Representations

David Wadden, Ulme Wennberg, Yi Luan, Hannaneh Hajishirzi


Abstract
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform well at capturing relationships among entities in the same or adjacent sentences, while dynamic span graph updates model long-range cross-sentence relationships. For instance, propagating span representations via predicted coreference links can enable the model to disambiguate challenging entity mentions. Our code is publicly available at https://github.com/dwadden/dygiepp and can be easily adapted for new tasks or datasets.
Anthology ID:
D19-1585
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5784–5789
Language:
URL:
https://aclanthology.org/D19-1585
DOI:
10.18653/v1/D19-1585
Bibkey:
Cite (ACL):
David Wadden, Ulme Wennberg, Yi Luan, and Hannaneh Hajishirzi. 2019. Entity, Relation, and Event Extraction with Contextualized Span Representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5784–5789, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Entity, Relation, and Event Extraction with Contextualized Span Representations (Wadden et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1585.pdf
Attachment:
 D19-1585.Attachment.pdf
Code
 dwadden/dygiepp +  additional community code
Data
ACE 2005GENIASciERC