Document Intelligence Metrics for Visually Rich Document Evaluation

The processing of Visually-Rich Documents (VRDs) is highly important in information extraction tasks associated with Document Intelligence. We introduce DI-Metrics, a Python library devoted to VRD model evaluation comprising text-based, geometric-based and hierarchical metrics for information extrac...

Full description

Saved in:
Bibliographic Details
Main Authors DeGange, Jonathan, Gupta, Swapnil, Han, Zhuoyu, Wilkosz, Krzysztof, Karwan, Adam
Format Journal Article
LanguageEnglish
Published 23.05.2022
Subjects
Computer Science - Artificial Intelligence
Online AccessGet full text

Cover

More Information
Summary:The processing of Visually-Rich Documents (VRDs) is highly important in information extraction tasks associated with Document Intelligence. We introduce DI-Metrics, a Python library devoted to VRD model evaluation comprising text-based, geometric-based and hierarchical metrics for information extraction tasks. We apply DI-Metrics to evaluate information extraction performance using publicly available CORD dataset, comparing performance of three SOTA models and one industry model. The open-source library is available on GitHub.
DOI:10.48550/arxiv.2205.11215