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

This paper describes our multiclass classification system developed as partof the LTEDI@RANLP-2023 shared task. We used a BERT-based language model todetect homophobic and transphobic content in social media comments across fivelanguage conditions: English, Spanish, Hindi, Malayalam, and Tamil. Weretrained a transformer-based crosslanguage pretrained language model,XLMRoBERTa, with spatially and temporally relevant social media language data.We also retrained a subset of models with simulated script-mixed social medialanguage data with varied performance. We developed the best performingseven-label classification system for Malayalam based on weighted macroaveraged F1 score (ranked first out of six) with variable performance for otherlanguage and class-label conditions. We found the inclusion of thisspatio-temporal data improved the classification performance for all languageand task conditions when compared with the baseline. The results suggests thattransformer-based language classification systems are sensitive toregister-specific and language-specific retraining.

cantnlp@LT-EDI-2023: Homophobia/Transphobia Detection in Social Media Comments using Spatio-Temporally Retrained Language Models