Multi-granularity sequential neural network for document-level biomedical relation extraction

Abstract Document-level biomedical relation extraction aims to extract the relation between multiple mentions of entities throughout an entire document. However, most methods suffer from long-distance context dependency and complex semantics causing by numerous biomedical entities and inter-sentence relations. In this paper, we propose a multi-granularity sequential network (MGSN) for document-level relation extraction to solve above problems. The proposed method learns to extract the document-level entity relation by the accumulation of document-level information and entity-level information including global and local entity information. In addition, some target entity pairs that reflect target entity relations can be extracted and paid more attention by CNN-based bi-affine structure. Experimental results on three document-level biomedical datasets demonstrate the effectiveness of the proposed model. Our code is available from http://github.com/SCUT-CCNL/MGSN .