Joint Model of Entity Recognition and Relation Extraction with Self-attention Mechanism

Abstract

In recent years, the joint model of entity recognition (ER) and relation extraction (RE) has attracted more and more attention in the healthcare and medical domains. However, there are some problems with the prior work. The joint model cannot extract all the relations for a specific entity, and the majority of joint models heavily rely on complex artificial features or professional natural language processing (NLP) tools. In this article, we construct a novel joint model that can simultaneously extract all medical entities and relations from medicine Chinese instructions. Moreover, the self-attention mechanism is introduced to the joint model to learn word intra-sentence dependencies. The proposed model is evaluated using a medicine Chinese instruction dataset that we collect and an open dataset provided in CoNLL-2004. Experimental results show that the model with self-attention achieves the state-of-the-art performance.