2024/04/19 by Hoang H. Nguyen, Nguyen, Hoang H., Chenwei Zhang +9 · 1 citation
Social Sciences · #Artificial Intelligence (cs.AI) #Artificial intelligence #Benchmark (surveying) #Cartography #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Geography #Historical Geopolitical and Social Dynamics #Linguistics #Machine Learning (cs.LG) #Natural language processing #Parallel computing #Philosophy #Programming language #Romanization #Scripting language #Transfer (computing)
paper · pdf · doi:10.48550/arxiv.2404.12618
openalex publication_date 2024/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Naively assuming English as a source language may hinder cross-lingual transfer for many languages by failing to consider the importance of language contact. Some languages are more well-connected than others, and target languages can benefit from transferring from closely related languages; for many languages, the set of closely related languages does not include English. In this work, we study the impact of source language for cross-lingual transfer, demonstrating the importance of selecting source languages that have high contact with the target language. We also construct a novel benchmark dataset for close contact Chinese-Japanese-Korean-Vietnamese (CJKV) languages to further encourage in-depth studies of language contact. To comprehensively capture contact between these languages, we propose to integrate Romanized transcription beyond textual scripts via Contrastive Learning objectives, leading to enhanced cross-lingual representations and effective zero-shot cross-lingual transfer.