Jun, 2023

ICDAR 2023 结构化文本提取竞赛之视觉丰富文档图像

TL;DRICDAR 2023 competition on Structured text extraction from Visually-Rich Document images (SVRD) organized with two tracks for evaluating end-to-end Complex Entity Linking and Labeling and Zero-shot / Few-shot Structured Text extraction respectively, with more than 50 types of visually-rich document images from enterprise applications, attracting 35 and 15 participants respectively and revealing a large gap in expected information extraction performance for complex and zero-shot scenarios.