Parallel Tokenizers: Rethinking Encoder Models' Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages 文章

ArXiv CS.CL2026-07-28PAPERen作者: Muhammad Dehan Al Kautsar, Fajri Koto

Parallel Tokenizers: Rethinking Encoder Models' Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages · 相关技术