ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
This work is significant for researchers and practitioners working with PLMs in NLP, as it offers an incremental improvement in understanding entities and relations, especially beneficial in data-scarce scenarios.
This paper addresses the limitation of conventional pre-trained language models in explicitly modeling relational facts. The authors propose ERICA, a contrastive learning framework with two novel pre-training tasks: entity discrimination and relation discrimination. ERICA improves typical PLMs like BERT and RoBERTa on relation extraction, entity typing, and question answering tasks, particularly in low-resource settings.
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.