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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recent grid-based document representations like BERTgrid allow thesimultaneous encoding of the textual and layout information of a document in a2D feature map so that state-of-the-art image segmentation and/or objectdetection models can be straightforwardly leveraged to extract key informationfrom documents. However, such methods have not achieved comparable performanceto state-of-the-art sequence- and graph-based methods such as LayoutLM and PICKyet. In this paper, we propose a new multi-modal backbone network byconcatenating a BERTgrid to an intermediate layer of a CNN model, where theinput of CNN is a document image and the BERTgrid is a grid of word embeddings,to generate a more powerful grid-based document representation, namedViBERTgrid. Unlike BERTgrid, the parameters of BERT and CNN in our multimodalbackbone network are trained jointly. Our experimental results demonstrate thatthis joint training strategy improves significantly the representation abilityof ViBERTgrid. Consequently, our ViBERTgrid-based key information extractionapproach has achieved state-of-the-art performance on real-world datasets.

ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents