Ying Wei, Qi Li
2022 Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining  
Relation extraction (RE) is an important task for many natural language processing applications. Document-level relation extraction task 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
more » ... urther 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 paths from one entity to the other. In addition, we propose an adaptive margin loss to address the long-tailed multi-label problem of document-level RE tasks, where multiple relations can be expressed in a document for an entity pair and there are a few popular relations. The loss function aims to encourage separations between positive and negative classes. The experimental results on datasets from various domains demonstrate the effectiveness of the proposed methods. CCS CONCEPTS • Computing methodologies → Natural language processing; Information extraction.
doi:10.1145/3534678.3539304 fatcat:ke3pousmg5etjdyl72zpbime7e