MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914653425106944 |
|---|---|
| author | Lee, Patrick Trujillo, Alain Chirino Plancarte, Diana Cuevas Ojo, Olumide Ebenezer Liu, Xinyi Shode, Iyanuoluwa Zhao, Yuan Peng, Jing Feldman, Anna |
| author_facet | Lee, Patrick Trujillo, Alain Chirino Plancarte, Diana Cuevas Ojo, Olumide Ebenezer Liu, Xinyi Shode, Iyanuoluwa Zhao, Yuan Peng, Jing Feldman, Anna |
| contents | This study investigates the computational processing of euphemisms, a universal linguistic phenomenon, across multiple languages. We train 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14526 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms Lee, Patrick Trujillo, Alain Chirino Plancarte, Diana Cuevas Ojo, Olumide Ebenezer Liu, Xinyi Shode, Iyanuoluwa Zhao, Yuan Peng, Jing Feldman, Anna Computation and Language This study investigates the computational processing of euphemisms, a universal linguistic phenomenon, across multiple languages. We train 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. |
| title | MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.14526 |