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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Event coreference resolution(ECR) is an important task in Natural LanguageProcessing (NLP) and nearly all the existing approaches to this task rely onevent argument information. However, these methods tend to suffer from errorpropagation from the stage of event argument extraction. Besides, not everyevent mention contains all arguments of an event, and argument information mayconfuse the model that events have arguments to detect event coreference inreal text. Furthermore, the context information of an event is useful to inferthe coreference between events. Thus, in order to reduce the errors propagatedfrom event argument extraction and use context information effectively, wepropose a multi-loss neural network model that does not need any argumentinformation to do the within-document event coreference resolution task andachieve a significant performance than the state-of-the-art methods.

Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information