Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya

Excerpt

arXiv:2607.15209v2 Announce Type: replace Abstract: Multilingual pre-trained language models such as XLM-R perform well for major languages but struggle with low-resource Ge'ez-script languages, largely due to high out-of-vocabulary (OOV) rates and excessive subword fragmentation from Latin-script-centric tokenizers. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting Amharic and Tigrinya. We train language-specific SentencePiece tokenizers on curated monolingual corpora, exten