%0 Conference Proceedings
%T MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms
%A Lee, Patrick
%A Chirino Trujillo, Alain
%A Cuevas Plancarte, Diana
%A Ojo, Olumide
%A Liu, Xinyi
%A Shode, Iyanuoluwa
%A Zhao, Yuan
%A Feldman, Anna
%A Peng, Jing
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F lee-etal-2024-meds
%X Euphemisms are found across the world‘s languages, making them a universal linguistic phenomenon. As such, euphemistic data may have useful properties for computational tasks across languages. In this study, we explore this premise by training a multilingual transformer model (XLM-RoBERTa) to disambiguate potentially euphemistic terms (PETs) in multilingual and cross-lingual settings. In line with current trends, we demonstrate that zero-shot learning across languages takes place. We also show cases where multilingual models perform better on the task compared to monolingual models by a statistically significant margin, indicating that multilingual data presents additional opportunities for models to learn about cross-lingual, computational properties of euphemisms. In a follow-up analysis, we focus on universal euphemistic “categories” such as death and bodily functions among others. We test to see whether cross-lingual data of the same domain is more important than within-language data of other domains to further understand the nature of the cross-lingual transfer.
%U https://aclanthology.org/2024.findings-eacl.59/
%P 875-881