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

Entity recognition is a fundamental task in understanding document images.Traditional sequence labeling frameworks treat the entity types as class IDsand rely on extensive data and high-quality annotations to learn semanticswhich are typically expensive in practice. In this paper, we aim to build anentity recognition model requiring only a few shots of annotated documentimages. To overcome the data limitation, we propose to leverage the labelsurface names to better inform the model of the target entity type semanticsand also embed the labels into the spatial embedding space to capture thespatial correspondence between regions and labels. Specifically, we go beyondsequence labeling and develop a novel label-aware seq2seq framework, LASER. Theproposed model follows a new labeling scheme that generates the label surfacenames word-by-word explicitly after generating the entities. During training,LASER refines the label semantics by updating the label surface namerepresentations and also strengthens the label-region correlation. In this way,LASER recognizes the entities from document images through both semantic andlayout correspondence. Extensive experiments on two benchmark datasetsdemonstrate the superiority of LASER under the few-shot setting.

Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework