Impact of Sequential Fine-Tuning on Zero-Shot Euphemism Detection in Low-Resource Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
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 sequential fine-tuning on typologically related versus unrelated source languages impact zero-shot accuracy for euphemism detection in low-resource languages on the XTREME-R benchmark?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.7/10.
Similar
Adaptive Batch Sampling in Sequential Fine-Tuning for XLM-R Zero-Shot Euphemism Detection in Low-Resource LanguagesSequential Fine-Tuning Language Variation in Zero-Shot Euphemism DetectionSequential Fine-Tuning Ordering for Cross-Lingual Euphemism Detection in Low-Resource LanguagesMultimodal Pretraining and Sequential Fine-Tuning for Zero-Shot Cross-Lingual Euphemism DetectionFine-tuning Impact on Zero-shot XTREME-R Performance in Low-resource LanguagesSequential Fine-Tuning of XLM-R-Large for Low-Resource Euphemism Detection