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

Information extraction from documents is a ubiquitous first step in manybusiness applications. During this step, the entries of various fields mustfirst be read from the images of scanned documents before being furtherprocessed and inserted into the corresponding databases. While many differentmethods have been developed over the past years in order to automate the aboveextraction step, they all share the requirement of bounding-box or text segmentannotations of their training documents. In this work we present DocReader, anend-to-end neural-network-based information extraction solution which can betrained using solely the images and the target values that need to be read. TheDocReader can thus leverage existing historical extraction data, completelyeliminating the need for any additional annotations beyond what is naturallyavailable in existing human-operated service centres. We demonstrate that theDocReader can reach and surpass other methods which require bounding-boxes fortraining, as well as provide a clear path for continual learning during itsdeployment in production.

DocReader: Bounding-Box Free Training of a Document Information Extraction Model