Collective prompt tuning with relation inference for document-level relation extraction

• Main Authors: YUAN, Changsen, CAO, Yixin, HUANG, Heyan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Natural language processing; Document-level relation extraction; Prompt-tuning; Various templates; Global reasoning; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/8298
• Institution: Singapore Management University

Document-level relation extraction (RE) aims to extract the relation of entities that may be across sentences. Existing methods mainly rely on two types of techniques: Pre-trained language models (PLMs) and reasoning skills. Although various reasoning methods have been proposed, how to elicit learnt...