@article{salice-etal-2026-insights,
    title = "Insights from {R}omanized {M}anipuri Social Media Text: A Transliteration Corpus and Variation Analysis",
    author = "Salice, Maisang Kamei  and
      Ranbir Singh, Sanasam  and
      Sarmah, Priyankoo",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.147/",
    pages = "1878--1888",
    abstract = "This paper presents the first large-scale study of Romanized Manipuri, a low-resource Indic language widely used by native speakers on social media. Social media text is highly informal and often noisy, posing challenges for natural language processing tasks; therefore, normalization through back-transliteration is essential. We construct a Romanized Manipuri to Manipuri{--}Bengali script back-transliteration corpus from YouTube comments, capturing diverse informal writing styles and orthographic variations. The dataset is analyzed to examine variation patterns at two levels: character-level inconsistencies and pragmatic stylistic variations influenced by user writing behavior. We also compare social media romanization with formal transliteration conventions, including standardized romanization schemes and textbook-based systems. Furthermore, we evaluate Transformer model at both character and subword levels and conduct a detailed error analyses to identify key challenges affecting back-transliteration performance."
}