Logo Lanfrica

snjev310/ByteChunk

Domain:

natural language processing

Record type:

paper
Creator:
snj
Host:
Repository for the EMNLP 2026 paper "When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages". # ByteChunk Byte-level dynamic chunking for zero-shot transfer to extremely low-resource languages. EMNLP 2026.