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

The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions andcauses as pairs from documents. We observe that the relative distancedistribution of emotions and causes is extremely imbalanced in the typical ECPEdataset. Existing methods have set a fixed size window to capture relationsbetween neighboring clauses. However, they neglect the effective semanticconnections between distant clauses, leading to poor generalization abilitytowards position-insensitive data. To alleviate the problem, we propose a novelMulti-Granularity Semantic Aware Graph model (MGSAG) to incorporatefine-grained and coarse-grained semantic features jointly, without regard todistance limitation. In particular, we first explore semantic dependenciesbetween clauses and keywords extracted from the document that conveyfine-grained semantic features, obtaining keywords enhanced clauserepresentations. Besides, a clause graph is also established to modelcoarse-grained semantic relations between clauses. Experimental resultsindicate that MGSAG surpasses the existing state-of-the-art ECPE models.Especially, MGSAG outperforms other models significantly in the condition ofposition-insensitive data.

Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction