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
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.
BibTeX
@inproceedings{qin-etal-2021-erica,
title = "{ERICA}: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning",
author = "Qin, Yujia and
Lin, Yankai and
Takanobu, Ryuichi and
Liu, Zhiyuan and
Li, Peng and
Ji, Heng and
Huang, Minlie and
Sun, Maosong and
Zhou, Jie",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "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 = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.260/",
doi = "10.18653/v1/2021.acl-long.260",
pages = "3350--3363"
}