Improving Graph-based Document-Level Relation Extraction Model with Novel Graph Structure

Abstract

Document-level relation extraction is a natural language processing task for extracting relations among entities in a document. Compared with sentence-level relation extraction, there are more challenges to document-level relation extraction. To acquire mutual information among entities in a document, recent studies have designed mention-level graphs or improved pretrained language models based on co-occurrence or coreference information. However, these methods cannot utilize the anaphoric information of pronouns, which play an important role in document-level relation extraction. In addition, there is a possibility of losing lexical information of the relations among entities directly expressed in a sentence. To address this issue, we propose two novel graph structures: an anaphoric graph and a local-context graph. The proposed method outperforms the existing graph-based relation extraction method when applying the document-level relation extraction dataset, DocRED.