Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Contrastive Learning Effects on Zero-Shot Cross-Lingual Euphemism Detection in XLM-R Fine-Tuning

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Euphemisms are culturally variable and often ambiguous, posing challenges for language models, especially in low-resource settings. This paper investigates how cross-lingual transfer via sequential fine-tuning affects euphemism detection across five languages: English, Spanish, Chinese, Turkish, and Yoruba. We compare sequential fine-tuning with monolingual and simultaneous fine-tuning using XLM-R and mBERT, analyzing how performance is shaped by language pairings, typological features, and pretraining coverage. Results show that sequential fine-tuning with a high-resource L1 improves L2 perfo Research goal: How does contrastive learning with typologically diverse language pairs (e.g., English-Turkish vs. English-Yoruba) during XLM-R sequential fine-tuning affect zero-shot cross-lingual euphemism detection accuracy on XTREME-R compared to random language pairings? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.

Visit

doi.org

Languages

Yoruba

Tags

contrastivelearningtypologicallydiverselanguagepairsEnglish-TurkishEnglish-Yoruba

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Contrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-RIntermediate Language Fine-Tuning for Cross-Lingual Euphemism Detection in XLM-RCross-lingual Euphemism Detection Accuracy in Sequential XLM-R-Large Fine-tuningContrastive Learning Effects on XLM-R Zero-Shot Cross-Lingual Transfer in Low-Resource LanguagesContrastive Learning and Adversarial Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual TasksCross-lingual Euphemism Detection Performance in XLM-R-Large: Sequential vs. Simultaneous Fine-tuning

Contrastive-Adversarial Fine-Tuning for Zero-Shot Cross-Lingual Performance in XLM-R

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Intermediate Language Fine-Tuning for Cross-Lingual Euphemism Detection in XLM-R

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec

Cross-lingual Euphemism Detection Accuracy in Sequential XLM-R-Large Fine-tuning

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec

Contrastive Learning Effects on XLM-R Zero-Shot Cross-Lingual Transfer in Low-Resource Languages

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Contrastive Learning and Adversarial Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual Tasks

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Cross-lingual Euphemism Detection Performance in XLM-R-Large: Sequential vs. Simultaneous Fine-tuning

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, espec