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

One of the major challenges in coreference resolution is how to make use ofentity-level features defined over clusters of mentions rather than mentionpairs. However, coreferent mentions usually spread far apart in an entire text,which makes it extremely difficult to incorporate entity-level features. Wepropose a graph neural network-based coreference resolution method that cancapture the entity-centric information by encouraging the sharing of featuresacross all mentions that probably refer to the same real-world entity. Mentionsare linked to each other via the edges modeling how likely two linked mentionspoint to the same entity. Modeling by such graphs, the features betweenmentions can be shared by message passing operations in an entity-centricmanner. A global inference algorithm up to second-order features is alsopresented to optimally cluster mentions into consistent groups. Experimentalresults show our graph neural network-based method combing with thesecond-order decoding algorithm (named GNNCR) achieved close tostate-of-the-art performance on the English CoNLL-2012 Shared Task dataset.

Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference