Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori
This addresses text normalization for under-resourced language communities, but it is incremental as it compares existing algorithms in new contexts.
The study tackled diacritic restoration for low-resource indigenous languages Bribri and Cook Islands Māori, finding that fine-tuned character-level LLMs perform best, with reliable performance emerging at data budgets of around 10,000 words.
We present experiments on diacritic restoration, a form of text normalization essential for natural language processing (NLP) tasks. Our study focuses on two extremely under-resourced languages: Bribri, a Chibchan language spoken in Costa Rica, and Cook Islands Māori, a Polynesian language spoken in the Cook Islands. Specifically, this paper: (i) compares algorithms for diacritics restoration in under-resourced languages, including tonal diacritics, (ii) examines the amount of data required to achieve target performance levels, (iii) contrasts results across varying resource conditions, and (iv) explores the related task of diacritic correction. We find that fine-tuned, character-level LLMs perform best, likely due to their ability to decompose complex characters into their UTF-8 byte representations. In contrast, massively multilingual models perform less effectively given our data constraints. Across all models, reliable performance begins to emerge with data budgets of around 10,000 words. Zero-shot approaches perform poorly in all cases. This study responds both to requests from the language communities and to broader NLP research questions concerning model performance and generalization in under-resourced contexts.