[go: up one dir, main page]

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning

Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou


Abstract
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks. However, conventional pre-training objectives do not explicitly model relational facts in text, which are crucial for textual understanding. To address this issue, we propose a novel contrastive learning framework ERICA to obtain a deep understanding of the entities and their relations in text. Specifically, we define two novel pre-training tasks to better understand entities and relations: (1) the entity discrimination task to distinguish which tail entity can be inferred by the given head entity and relation; (2) the relation discrimination task to distinguish whether two relations are close or not semantically, which involves complex relational reasoning. Experimental results demonstrate that ERICA can improve typical PLMs (BERT and RoBERTa) on several language understanding tasks, including relation extraction, entity typing and question answering, especially under low-resource settings.
Anthology ID:
2021.acl-long.260
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3350–3363
Language:
URL:
https://aclanthology.org/2021.acl-long.260
DOI:
10.18653/v1/2021.acl-long.260
Bibkey:
Cite (ACL):
Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, and Jie Zhou. 2021. ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3350–3363, Online. Association for Computational Linguistics.
Cite (Informal):
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (Qin et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.260.pdf
Video:
 https://aclanthology.org/2021.acl-long.260.mp4
Code
 thunlp/ERICA
Data
DocREDMRQASQuADSemEval-2010 Task-8TriviaQAWikiHop