Document-level relation extraction via separate relation representation and logical reasoning

• Main Authors: HUANG, Heyan, YUAN, Changsen, LIU, Qian, CAO, Yixin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: document-level relation extraction; separate relation representation; logical reasoning; relational reasoning; computing methodologies; information extraction; atural language processing; mention-level; Artificial Intelligence and Robotics; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8255; https://ink.library.smu.edu.sg/context/sis_research/article/9258/viewcontent/Document_level_Relation_Ext_av.pdf
• Institution: Singapore Management University

Document-level relation extraction (RE) extends the identification of entity/mentions’ relation from the single sentence to the long document. It is more realistic and poses new challenges to relation representation and reasoning skills. In this article, we propose a novel model, SRLR, using Separate Relation Representation and Logical Reasoning considering the indirect relation representation and complex reasoning of evidence sentence problems. Specifically, we first expand the judgment of relational facts from the entity-level to the mention-level, highlighting fine-grained information to capture the relation representation for the entity pair. Second, we propose a logical reasoning module to identify evidence sentences and conduct relational reasoning. Extensive experiments on two publicly available benchmark datasets demonstrate the effectiveness of our proposed SRLR as compared to 19 baseline models. Further ablation study also verifies the effects of the key components.