Joint Extraction of Entities and Relations with a Hierarchical Multi-task Tagging Model

Entity extraction and relation extraction are two indispensable building blocks for knowledge graph construction. Recent works on entity and relation extraction have shown the superiority of solving the two problems in a joint manner, where entities and relations are extracted simultaneously to form relational triples in a knowledge graph. However, existing methods ignore the hierarchical semantic interdependency between entity extraction (EE) and joint extraction (JE), which leaves much to be desired in real applications. In this work, we propose a hierarchical multi-task tagging model, called HMT, which captures such interdependency and achieves better performance for joint extraction of entities and relations. Specifically, the EE task is organized at the bottom layer and JE task at the top layer in a hierarchical structure. Furthermore, the learned semantic representation at the lower level can be shared by the upper level via multi-task learning. Experimental results demonstrate the effectiveness of the proposed model for joint extraction in comparison with the state-of-the-art methods.