Syntax-Informed Self-Attention Network for Span-Based Joint Entity and Relation Extraction

Current state-of-the-art joint entity and relation extraction framework is based on span-level entity classification and relation identification between pairs of entity mentions. However, while maintaining an efficient exhaustive search on spans, the importance of syntactic features is not taken into consideration. It will lead to a problem that the prediction of a relation between two entities is related based on corresponding entity types, but in fact they are not related in the sentence. In addition, although previous works have proven that extract local context is beneficial for the task, it still lacks in-depth learning of contextual features in local context. In this paper, we propose to incorporate syntax knowledge into multi-head self-attention by employing part of heads to focus on syntactic parents of each token from pruned dependency trees, and we use it to model the global context to fuse syntactic and semantic features. In addition, in order to get richer contextual features from the local context, we apply local focus mechanism on entity pairs and corresponding context. Based on applying the two strategies, we perform joint entity and relation extraction on span-level. Experimental results show that our model achieves significant improvements on both Conll04 and SciERC dataset compared to strong competitors.

Automated summary

The study proposes a framework that incorporates syntax knowledge and local focus mechanism into entity and relation extraction, significantly enhancing the model performance by fusing syntactic and semantic features as well as obtaining richer contextual features from local context.