March 5, 2024, 2:52 p.m. | Xudong Zhu, Zhao Kang, Bei Hui

cs.CL updates on arXiv.org arxiv.org

arXiv:2403.01886v1 Announce Type: new
Abstract: Document-level Relation Extraction (DocRE) aims to identify relation labels between entities within a single document. It requires handling several sentences and reasoning over them. State-of-the-art DocRE methods use a graph structure to connect entities across the document to capture dependency syntax information. However, this is insufficient to fully exploit the rich syntax information in the document. In this work, we propose to fuse constituency and dependency syntax into DocRE. It uses constituency syntax to aggregate …

abstract art arxiv cs.ai cs.cl document extraction graph identify information labels reasoning state syntax them type

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Senior Data Scientist

@ ITE Management | New York City, United States