HfGCN: Hierarchical fused GCN for Joint Entity and Relation Extraction

The extraction of entities and relations from un-structured text is crucial for information extraction. The joint models have been proposed to solve both tasks simultaneously. However, previous work only focuses on the linear representation of sentences and neglects hierarchical grammatical knowledge, which can be injected into the word representations to improve the accuracy of joint extraction. In this paper, we propose a joint model, integrating the fused syntax graph information into a hierarchical graph convolution model for joint extraction. Specifically, we use the attention mechanism to mine the implicit relations between words and dynamically fuse it with explicit dependency syntax graph to obtain fused graph, and through hierarchical graph convolution network to obtain the fused features of different granularity. Experimental results show that our model yields a significant performance compared with prior strong baselines in two datasets.