Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909973739470848 |
|---|---|
| author | Coto-Solano, Rolando Li, Daisy Ferraz, Manoela Teleginski Sasse, Olivia Krupka, Cha Loáiciga, Sharid Nicholas, Sally Akevai Tenamu |
| author_facet | Coto-Solano, Rolando Li, Daisy Ferraz, Manoela Teleginski Sasse, Olivia Krupka, Cha Loáiciga, Sharid Nicholas, Sally Akevai Tenamu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19630 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori Coto-Solano, Rolando Li, Daisy Ferraz, Manoela Teleginski Sasse, Olivia Krupka, Cha Loáiciga, Sharid Nicholas, Sally Akevai Tenamu Computation and Language 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. |
| title | Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.19630 |