SagDRE: Sequence-Aware Graph-Based Document-Level Relation Extraction with Adaptive Margin Loss

Anonymous

Abstract: Relation extraction (RE) is an important task for many natural language processing applications. Document-level relation extraction aims to extract the relations within a document and poses many challenges to the RE tasks as it requires reasoning across sentences and handling multiple relations expressed in the same document. Existing state-of-the-art document-level RE models use the graph structure to better connect long-distance correlations. In this work, we propose SagDRE model, which further considers and captures the original sequential information from the text. The proposed model learns sentence-level directional edges to capture the information flow in the document and uses the token-level sequential information to encode the shortest path from one entity to the other. In addition, we propose an adaptive margin loss to maximize the margins to separate positive and negative classes. The experimental results on datasets from various domains demonstrate the effectiveness of our proposed methods.