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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visually-rich Document Understanding (VrDU) has attracted much researchattention over the past years. Pre-trained models on a large number of documentimages with transformer-based backbones have led to significant performancegains in this field. The major challenge is how to fusion the differentmodalities (text, layout, and image) of the documents in a unified model withdifferent pre-training tasks. This paper focuses on improving text-layoutinteractions and proposes a novel multi-modal pre-training model, LayoutMask.LayoutMask uses local 1D position, instead of global 1D position, as layoutinput and has two pre-training objectives: (1) Masked Language Modeling:predicting masked tokens with two novel masking strategies; (2) Masked PositionModeling: predicting masked 2D positions to improve layout representationlearning. LayoutMask can enhance the interactions between text and layoutmodalities in a unified model and produce adaptive and robust multi-modalrepresentations for downstream tasks. Experimental results show that ourproposed method can achieve state-of-the-art results on a wide variety of VrDUproblems, including form understanding, receipt understanding, and documentimage classification.

LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding