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

With the increasing influence of social media platforms, it has becomecrucial to develop automated systems capable of detecting instances of sexismand other disrespectful and hateful behaviors to promote a more inclusive andrespectful online environment. Nevertheless, these tasks are considerablychallenging considering different hate categories and the author's intentions,especially under the learning with disagreements regime. This paper describesAI-UPV team's participation in the EXIST (sEXism Identification in SocialneTworks) Lab at CLEF 2023. The proposed approach aims at addressing the taskof sexism identification and characterization under the learning withdisagreements paradigm by training directly from the data with disagreements,without using any aggregated label. Yet, performances considering both soft andhard evaluations are reported. The proposed system uses large language models(i.e., mBERT and XLM-RoBERTa) and ensemble strategies for sexism identificationand classification in English and Spanish. In particular, our system isarticulated in three different pipelines. The ensemble approach outperformedthe individual large language models obtaining the best performances bothadopting a soft and a hard label evaluation. This work describes theparticipation in all the three EXIST tasks, considering a soft evaluation, itobtained fourth place in Task 2 at EXIST and first place in Task 3, with thehighest ICM-Soft of -2.32 and a normalized ICM-Soft of 0.79. The source code ofour approaches is publicly available athttps://github.com/AngelFelipeMP/Sexism-LLM-Learning-With-Disagreement.

AI-UPV at EXIST 2023 -- Sexism Characterization Using Large Language Models Under The Learning with Disagreements Regime