EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction

Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, Zhendong Mao


Abstract
Multi-triple extraction is a challenging task due to the existence of informative inter-triple correlations, and consequently rich interactions across the constituent entities and relations. While existing works only explore entity representations, we propose to explicitly introduce relation representation, jointly represent it with entities, and novelly align them to identify valid triples.We perform comprehensive experiments on document-level relation extraction and joint entity and relation extraction along with ablations to demonstrate the advantage of the proposed method.
Anthology ID:
2022.naacl-main.48
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:
659–665
Language:
URL:
https://aclanthology.org/2022.naacl-main.48
DOI:
10.18653/v1/2022.naacl-main.48
Bibkey:
Cite (ACL):
Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, and Zhendong Mao. 2022. EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 659–665, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction (Xu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.48.pdf
Video:
 https://aclanthology.org/2022.naacl-main.48.mp4
Code
 benfengxu/emrel
Data
DocRED