Workshop on Document Intelligence Understanding

TL;DR

This workshop focuses on advancing document understanding and information extraction across various domains, emphasizing full document comprehension through a new dataset and challenge to improve multi-page analysis techniques.

Contribution

It introduces the PDFVQA dataset and challenge, promoting research on full document-level understanding beyond single-page analysis.

Findings

Development of the PDFVQA dataset for full document understanding

Introduction of a challenge to evaluate models on multi-page document questions

Enhanced techniques for structural and contextual comprehension of documents

Abstract

Document understanding and information extraction include different tasks to understand a document and extract valuable information automatically. Recently, there has been a rising demand for developing document understanding among different domains, including business, law, and medicine, to boost the efficiency of work that is associated with a large number of documents. This workshop aims to bring together researchers and industry developers in the field of document intelligence and understanding diverse document types to boost automatic document processing and understanding techniques. We also released a data challenge on the recently introduced document-level VQA dataset, PDFVQA. The PDFVQA challenge examines the structural and contextual understandings of proposed models on the natural full document level of multiple consecutive document pages by including questions with a sequence of answers extracted from multi-pages of the full document. This task helps to boost the document understanding step from the single-page level to the full document level understanding.