@inproceedings{ravikiran-etal-2026-tokenizers,
    title = "Do Tokenizers Fail on Informal {H}indi Expressions? Evidence from Static, Downstream, and Robustness Analyses",
    author = "Ravikiran, Manikandan  and
      Tiwari, Tanmay  and
      Gupta, Vibhu  and
      Prakash, Rakesh  and
      Saluja, Rohit  and
      Mohanty, Shayan",
    editor = "Hettiarachchi, Hansi  and
      Ranasinghe, Tharindu  and
      Plum, Alistair  and
      Rayson, Paul  and
      Mitkov, Ruslan  and
      Gaber, Mohamed  and
      Premasiri, Damith  and
      Tan, Fiona Anting  and
      Uyangodage, Lasitha",
    booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.loreslm-1.2/",
    pages = "13--28",
    ISBN = "979-8-89176-377-7",
    abstract = "We present, to our knowledge, the first systematic evaluation of tokenization quality for \textit{informal Hindi expressions}, combining static, downstream, and robustness analyses. Our investigation centers on three questions: (RQ1) how well tokenizers preserve informal expression units using static boundary and integrity metrics, (RQ2) how tokenization choices affect downstream identification of informal expressions, and (RQ3) how robust tokenizers remain under orthographic variation, romanization, and noisy spelling. Across multilingual, Indic-focused, and byte-level tokenizers, we find that Indic-oriented models (e.g., MuRIL, IndicBERT) preserve expression boundaries better and achieve higher downstream F1 on clean text than generic multilingual models (e.g., mBERT, XLM-R). However, all tokenizers exhibit severe degradation under romanization, with phrase integrity rates approaching zero. These findings demonstrate that tokenization constitutes a hidden but critical bottleneck for informal Hindi NLP, particularly in cross-script settings, and motivate the need for tokenization strategies that explicitly account for phrase-level semantics and orthographic variation."
}