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

Identifying related entities and events within and across documents isfundamental to natural language understanding. We present an approach to entityand event coreference resolution utilizing contrastive representation learning.Earlier state-of-the-art methods have formulated this problem as a binaryclassification problem and leveraged large transformers in a cross-encoderarchitecture to achieve their results. For large collections of documents andcorresponding set of $n$ mentions, the necessity of performing $n^{2}$transformer computations in these earlier approaches can be computationallyintensive. We show that it is possible to reduce this burden by applyingcontrastive learning techniques that only require $n$ transformer computationsat inference time. Our method achieves state-of-the-art results on a number ofkey metrics on the ECB+ corpus and is competitive on others.

Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities