@inproceedings{nyalang-2026-beyond,
    title = "Beyond Multilinguality: Typological Limitations in Multilingual Models for {M}eitei Language",
    author = "Nyalang, Badal",
    editor = "Vylomova, Ekaterina  and
      Shcherbakov, Andrei  and
      Rani, Priya",
    booktitle = "Proceedings of the 8th Workshop on Research in Computational Linguistic Typology and Multilingual {NLP}",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/credits/2026.sigtyp-main.5/",
    pages = "32--38",
    ISBN = "979-8-89176-374-6",
    abstract = "We present MeiteiRoBERTa, the first publicly available monolingual RoBERTa-based language model for Meitei (Manipuri), a low-resource language spoken by over 1.8 million people in Northeast India. Trained from scratch on 76 million words of Meitei text in Bengali script, our model achieves a perplexity of 65.89, representing a 5.2{\texttimes} improvement over multilingual baselines BERT (341.56) and MuRIL (355.65). Through comprehensive evaluation on perplexity, tokenization efficiency, and semantic representation quality, we demonstrate that domain-specific pre training significantly outperforms general-purpose multilingual models for low-resource languages. Our model exhibits superior semantic understanding with 0.769 similarity separation compared to 0.035 for mBERT and near-zero for MuRIL, despite MuRIL{'}s better tokenization efficiency (fertility: 3.29 vs. 4.65). We publicly release the model, training code, and datasets to accelerate NLP research for Meitei and other underrepresented Northeast Indian languages"
}