Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document

• Published in: arXiv.org
• Main Authors: Chen, Xiangnan, Xiao, Qian, Li, Juncheng, Dong, Duo, Lin, Jun, Liu, Xiaozhong, Tang, Siliang
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 27.10.2023
• Subjects: Documents; Iterative methods; Knowledge representation

Visual Relation Extraction (VRE) is a powerful means of discovering relationships between entities within visually-rich documents. Existing methods often focus on manipulating entity features to find pairwise relations, yet neglect the more fundamental structural information that links disparate ent...