Deep Learning Representations in Automatic Misogyny Identification: What Do We Gain and What Do We Miss?
Fiche du document
20 octobre 2022
- doi: 10.4000/books.aaccademia.10914
- eisbn: 9791280136947
https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess
Mots-clés
linguistica computazionale linguistica linguistique computationelle linguistique Computational Linguistics Language Linguistics LAN009000 Linguistics CFSujets proches
Language (New words, slang, etc.) Field guides Keys (Identification guides) Identification guides Women-hating Linguistic science Science of language Forensic identificationCiter ce document
Elisabetta Fersini et al., « Deep Learning Representations in Automatic Misogyny Identification: What Do We Gain and What Do We Miss? », Accademia University Press, ID : 10.4000/books.aaccademia.10914
Métriques
Partage / Export
Résumé
In this paper, we address the problem of automatic misogyny identification focusing on understanding the representation capabilities of widely adopted embeddings and addressing the problem of unintended bias. The proposed framework, grounded on Sentence Embeddings and Multi-Objective Bayesian Optimization, has been validated on an Italian dataset. We highlight capabilities and weaknesses related to the use of pre-trained language, as well as the contribution of Bayesian Optimization for mitigating the problem of biased predictions.