嵌入相似性能否预测跨语言迁移?针对非洲语言的系统研究
Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages
AI总结:
本文通过系统评估五种嵌入相似性度量,发现余弦间隙和检索度量能有效预测跨语言迁移成功,同时揭示了模型特定分析的重要性。
摘要:
跨语言迁移对于构建面向低资源非洲语言的NLP系统至关重要,但从业者缺乏可靠的方法来选择源语言。我们系统地评估了五种嵌入相似性度量标准,涵盖816次迁移实验,涉及三个NLP任务、三个以非洲为中心的多语言模型和来自四个语言家族的12种语言。我们发现,余弦间隙和基于检索的度量(P@1、CSLS)能够可靠地预测迁移成功度(ρ=0.4-0.6),而CKA的预测能力极低(ρ≈0.1)。关键的是,当跨模型汇总时,相关性符号会反转(辛普森悖论),因此从业者必须逐个模型验证。嵌入度量在预测能力上与URIEL语言类型学相当。我们的结果为源语言选择提供了具体的指导,并突显了模型特定分析的重要性。
英文摘要:
Cross-lingual transfer is essential for building NLP systems for low-resource African languages, but practitioners lack reliable methods for selecting source languages. We systematically evaluate five embedding similarity metrics across 816 transfer experiments spanning three NLP tasks, three African-centric multilingual models, and 12 languages from four language families. We find that cosine gap and retrieval-based metrics (P@1, CSLS) reliably predict transfer success ($ρ= 0.4-0.6$), while CKA shows negligible predictive power ($ρ\approx 0.1$). Critically, correlation signs reverse when pooling across models (Simpson's Paradox), so practitioners must validate per-model. Embedding metrics achieve comparable predictive power to URIEL linguistic typology. Our results provide concrete guidance for source language selection and highlight the importance of model-specific analysis.
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。