作者位次 #2/3ACL 2026Findings· Findings of ACL
One Script Instead of Hundreds? On Pretraining R omanized Encoder Language Models
Benedikt Ebing · Lennart Keller · Goran Glavaš
摘要
Exposing latent lexical overlap, script romanization has emerged as an effective strategy for improving cross-lingual transfer (XLT) in multilingual language models (mLMs). Most prior work, however, focused on setups that favor romanization the most: (1) transfer from high-resource Latin-script t...