语言迁移何时有帮助？面向跨语言委婉语检测的顺序微调
When Does Language Transfer Help? Sequential Fine-Tuning for Cross-Lingual Euphemism Detection
AI总结：
本文研究顺序微调对跨语言委婉语检测的影响，发现高资源L1顺序微调可提升低资源L2性能，XLM-R增益大但易遗忘，mBERT更稳定，证明该方法简单有效。
摘要：
委婉语具有文化差异性且常常存在歧义，这给语言模型带来了挑战，尤其是在低资源场景下。本文研究了通过顺序微调实现的跨语言迁移如何影响五种语言（英语、西班牙语、中文、土耳其语和约鲁巴语）中的委婉语检测。我们使用XLM-R和mBERT，将顺序微调与单语微调和同时微调进行比较，分析了语言配对、类型学特征和预训练覆盖范围如何塑造性能。结果表明，使用高资源L1进行顺序微调能够提升L2的性能，尤其是对于约鲁巴语和土耳其语等低资源语言。XLM-R取得了更大的提升，但对预训练差距和灾难性遗忘更为敏感，而mBERT的结果虽然较低但更稳定。这些发现凸显了顺序微调是一种简单而有效的策略，可在多语言模型中改进委婉语检测，尤其是在涉及低资源语言时。
英文摘要：
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 performance, especially for low-resource languages like Yoruba and Turkish. XLM-R achieves larger gains but is more sensitive to pretraining gaps and catastrophic forgetting, while mBERT yields more stable, though lower, results. These findings highlight sequential fine-tuning as a simple yet effective strategy for improving euphemism detection in multilingual models, particularly when low-resource languages are involved.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
