KyrgyzBERT: A Compact, Efficient Language Model for Kyrgyz NLP
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911285238562816 |
|---|---|
| author | Metinov, Adilet Kudakeeva, Gulida M. Kabaeva, Gulnara D. |
| author_facet | Metinov, Adilet Kudakeeva, Gulida M. Kabaeva, Gulnara D. |
| contents | Kyrgyz remains a low-resource language with limited foundational NLP tools. To address this gap, we introduce KyrgyzBERT, the first publicly available monolingual BERT-based language model for Kyrgyz. The model has 35.9M parameters and uses a custom tokenizer designed for the language's morphological structure. To evaluate performance, we create kyrgyz-sst2, a sentiment analysis benchmark built by translating the Stanford Sentiment Treebank and manually annotating the full test set. KyrgyzBERT fine-tuned on this dataset achieves an F1-score of 0.8280, competitive with a fine-tuned mBERT model five times larger. All models, data, and code are released to support future research in Kyrgyz NLP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KyrgyzBERT: A Compact, Efficient Language Model for Kyrgyz NLP Metinov, Adilet Kudakeeva, Gulida M. Kabaeva, Gulnara D. Computation and Language I.2.7 Kyrgyz remains a low-resource language with limited foundational NLP tools. To address this gap, we introduce KyrgyzBERT, the first publicly available monolingual BERT-based language model for Kyrgyz. The model has 35.9M parameters and uses a custom tokenizer designed for the language's morphological structure. To evaluate performance, we create kyrgyz-sst2, a sentiment analysis benchmark built by translating the Stanford Sentiment Treebank and manually annotating the full test set. KyrgyzBERT fine-tuned on this dataset achieves an F1-score of 0.8280, competitive with a fine-tuned mBERT model five times larger. All models, data, and code are released to support future research in Kyrgyz NLP. |
| title | KyrgyzBERT: A Compact, Efficient Language Model for Kyrgyz NLP |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2511.20182 |