TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zmigrod, Ran, Ma, Zhiqiang, Nourbakhsh, Armineh, Shah, Sameena
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910322327027712
author Zmigrod, Ran
Ma, Zhiqiang
Nourbakhsh, Armineh
Shah, Sameena
author_facet Zmigrod, Ran
Ma, Zhiqiang
Nourbakhsh, Armineh
Shah, Sameena
contents Visually Rich Form Understanding (VRFU) poses a complex research problem due to the documents' highly structured nature and yet highly variable style and content. Current annotation schemes decompose form understanding and omit key hierarchical structure, making development and evaluation of end-to-end models difficult. In this paper, we propose a novel F1 metric to evaluate form parsers and describe a new content-agnostic, tree-based annotation scheme for VRFU: TreeForm. We provide methods to convert previous annotation schemes into TreeForm structures and evaluate TreeForm predictions using a modified version of the normalized tree-edit distance. We present initial baselines for our end-to-end performance metric and the TreeForm edit distance, averaged over the FUNSD and XFUND datasets, of 61.5 and 26.4 respectively. We hope that TreeForm encourages deeper research in annotating, modeling, and evaluating the complexities of form-like documents.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05282
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing
Zmigrod, Ran
Ma, Zhiqiang
Nourbakhsh, Armineh
Shah, Sameena
Computation and Language
Visually Rich Form Understanding (VRFU) poses a complex research problem due to the documents' highly structured nature and yet highly variable style and content. Current annotation schemes decompose form understanding and omit key hierarchical structure, making development and evaluation of end-to-end models difficult. In this paper, we propose a novel F1 metric to evaluate form parsers and describe a new content-agnostic, tree-based annotation scheme for VRFU: TreeForm. We provide methods to convert previous annotation schemes into TreeForm structures and evaluate TreeForm predictions using a modified version of the normalized tree-edit distance. We present initial baselines for our end-to-end performance metric and the TreeForm edit distance, averaged over the FUNSD and XFUND datasets, of 61.5 and 26.4 respectively. We hope that TreeForm encourages deeper research in annotating, modeling, and evaluating the complexities of form-like documents.
title TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing
topic Computation and Language
url https://arxiv.org/abs/2402.05282