Discriminative reasoning with sparse event representation for document-level event-event relation extraction

• Main Authors: YUAN, Changsen, HUANG, Heyan, CAO, Yixin, WEN, Yonggang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Event graphs; Event representations; Extraction modeling; Information density; Joint models; Lower density; Prior-knowledge; Relation extraction; Sentence level; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8288; https://ink.library.smu.edu.sg/context/sis_research/article/9291/viewcontent/Discriminative_reasoning_with_sparse_event_representation_for_document_level_event_event_relation_extraction.pdf
• Institution: Singapore Management University

Document-level Event-Event Relation Extraction (DERE) aims to extract relations between events in a document. It challenges conventional sentence-level task (SERE) with difficult long-text understanding. In this paper, we propose a novel DERE model (SENDIR) for better document-level reasoning. Diffe...