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

We present a novel retrofitting method to induce emotion aspects intopre-trained language models (PLMs) such as BERT and RoBERTa. Our method updatespre-trained network weights using contrastive learning so that the textfragments exhibiting similar emotions are encoded nearby in the representationspace, and the fragments with different emotion content are pushed apart. Whiledoing so, it also ensures that the linguistic knowledge already present in PLMsis not inadvertently perturbed. The language models retrofitted by our method,i.e., BERTEmo and RoBERTaEmo, produce emotion-aware text representations, asevaluated through different clustering and retrieval metrics. For thedownstream tasks on sentiment analysis and sarcasm detection, they performbetter than their pre-trained counterparts (about 1% improvement in F1-score)and other existing approaches. Additionally, a more significant boost inperformance is observed for the retrofitted models over pre-trained ones infew-shot learning setting.

Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning