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

arXiv:2405.03104v1 Announce Type: new
Abstract: 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 …

abstract arxiv attention cs.cv document document understanding edge features framework graph key language methodology networks novel paper role type understanding value visual