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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Emotion-cause pair extraction (ECPE) is an emerging task aiming to extractpotential pairs of emotions and corresponding causes from documents. Previousapproaches have focused on modeling the pair-to-pair relationship and achievedpromising results. However, the clause-to-clause relationship, whichfundamentally symbolizes the underlying structure of a document, has still beenin its research infancy. In this paper, we define a novel clause-to-clauserelationship. To learn it applicably, we propose a general clause-levelencoding model named EA-GAT comprising E-GAT and Activation Sort. E-GAT isdesigned to aggregate information from different types of clauses; ActivationSort leverages the individual emotion/cause prediction and the sort-basedmapping to propel the clause to a more favorable representation. Since EA-GATis a clause-level encoding model, it can be broadly integrated with anyprevious approach. Experimental results show that our approach has asignificant advantage over all current approaches on the Chinese and Englishbenchmark corpus, with an average of $2.1\%$ and $1.03\%$.

Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction