GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Biescas, Nil, Boned, Carlos, Lladós, Josep, Biswas, Sanket
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911867995160576
author Biescas, Nil
Boned, Carlos
Lladós, Josep
Biswas, Sanket
author_facet Biescas, Nil
Boned, Carlos
Lladós, Josep
Biswas, Sanket
contents This paper presents GeoContrastNet, a language-agnostic framework to structured document understanding (DU) by integrating a contrastive learning objective with graph attention networks (GATs), emphasizing the significant role of geometric features. We propose a novel methodology that combines geometric edge features with visual features within an overall two-staged GAT-based framework, demonstrating promising results in both link prediction and semantic entity recognition performance. Our findings reveal that combining both geometric and visual features could match the capabilities of large DU models that rely heavily on Optical Character Recognition (OCR) features in terms of performance accuracy and efficiency. This approach underscores the critical importance of relational layout information between the named text entities in a semi-structured layout of a page. Specifically, our results highlight the model's proficiency in identifying key-value relationships within the FUNSD dataset for forms and also discovering the spatial relationships in table-structured layouts for RVLCDIP business invoices. Our code and pretrained models will be accessible on our official GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03104
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding
Biescas, Nil
Boned, Carlos
Lladós, Josep
Biswas, Sanket
Computer Vision and Pattern Recognition
This paper presents GeoContrastNet, a language-agnostic framework to structured document understanding (DU) by integrating a contrastive learning objective with graph attention networks (GATs), emphasizing the significant role of geometric features. We propose a novel methodology that combines geometric edge features with visual features within an overall two-staged GAT-based framework, demonstrating promising results in both link prediction and semantic entity recognition performance. Our findings reveal that combining both geometric and visual features could match the capabilities of large DU models that rely heavily on Optical Character Recognition (OCR) features in terms of performance accuracy and efficiency. This approach underscores the critical importance of relational layout information between the named text entities in a semi-structured layout of a page. Specifically, our results highlight the model's proficiency in identifying key-value relationships within the FUNSD dataset for forms and also discovering the spatial relationships in table-structured layouts for RVLCDIP business invoices. Our code and pretrained models will be accessible on our official GitHub.
title GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.03104