用嵌入相似性预测非洲语言跨语言迁移效果，找到有效指标。
Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages
- 测试五种相似性度量，发现余弦差和检索指标能可靠预测迁移效果。
- 相关系数达0.4-0.6，而CKA几乎无预测力（ρ≈0.1）。
- 不同模型结果相反，需按模型单独验证，适合低资源语言研究者。
跨语言迁移对构建低资源非洲语言的NLP系统至关重要，但从业者缺乏可靠的源语言选择方法。本文系统评估了五种嵌入相似性度量，在涵盖3个NLP任务、3个非洲语系多语言模型、12种来自四大语系语言的816次迁移实验中进行检验。结果表明，余弦差和基于检索的度量（P@1、CSLS）能可靠预测迁移成功（ρ=0.4–0.6），而CKA的预测能力可忽略不计（ρ≈0.1）。关键发现：跨模型合并数据时相关性符号反转（辛普森悖论），因此必须针对每个模型单独验证。嵌入相似性度量的预测能力与URIEL语言类型学相当。研究为源语言选择提供实证指导，并强调模型特异性分析的重要性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。