MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling

arXiv:2403.10691v1 Announce Type: cross
Abstract: A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts. Although contemporary text encoding methods cover most of the world's writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments …

abstract arxiv bias cs.ai cs.cl cs.lg diverse encoding global language languages major modeling multilingual scripts systems text type west world writing