English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Visual Information Extraction (VIE) task aims to extract key information frommultifarious document images (e.g., invoices and purchase receipts). Mostprevious methods treat the VIE task simply as a sequence labeling problem orclassification problem, which requires models to carefully identify each kindof semantics by introducing multimodal features, such as font, color, layout.But simply introducing multimodal features couldn't work well when faced withnumeric semantic categories or some ambiguous texts. To address this issue, inthis paper we propose a novel key-value matching model based on a graph neuralnetwork for VIE (MatchVIE). Through key-value matching based on relevancyevaluation, the proposed MatchVIE can bypass the recognitions to varioussemantics, and simply focuses on the strong relevancy between entities.Besides, we introduce a simple but effective operation, Num2Vec, to tackle theinstability of encoded values, which helps model converge more smoothly.Comprehensive experiments demonstrate that the proposed MatchVIE cansignificantly outperform previous methods. Notably, to the best of ourknowledge, MatchVIE may be the first attempt to tackle the VIE task by modelingthe relevancy between keys and values and it is a good complement to theexisting methods.

MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction