No AI summary available for this article.
Why It Matters
Multilingual language models transfer knowledge across languages through shared subword vocabulary, a mechanism that breaks down when related languages use different writing systems.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Multilingual language models transfer knowledge across languages through shared subword vocabulary, a mechanism that breaks down when related languages use different writing systems. Prior work addresses this via script equalization (romanization or IPA transcription), but direct comparisons are rare; the focus has been on encoder-only models, with most work adapting existing pretrained models. We systematically compare different input representations in autoregressive multilingual pretraining, comparing orthographic text, IPA, and romanization in a controlled setup across three scales (467M,...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.25904v1 · Indexed 19 days ago