@article{kumar-etal-2026-sentence,
    title = "Sentence-Level Back-Transliteration of {R}omanized {I}ndian Languages: Performance Analysis and Challenges",
    author = "Kumar, Saurabh  and
      Kakadiya, Dhruvkumar Babubhai  and
      Singh, Sanasam Ranbir  and
      Nandi, Sukumar",
    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.61/",
    pages = "818--827",
    abstract = "The widespread use of Romanized text for Indian languages, particularly on social media platforms, poses significant challenges for natural language processing due to the lack of standardized orthography and the presence of contextual ambiguities. In this study, we explore sentence-level back-transliteration for 13 Indian languages, focusing on addressing the limitations of word-level models that fail to capture contextual dependencies. We evaluate state-of-the-art models, including fine-tuned LLaMA, mT5, and Multilingual Transformer models, comparing their performance against the baseline IndicXlit model. In addition, we conduct a comprehensive error analysis to gain deeper insights into model performance. Our results demonstrate that fine-tuned LLaMA and the proposed IndiXform model, specifically designed to leverage sentence-level context, significantly outperform zero-shot LLaMA and the IndicXlit baseline. These findings provide valuable insights into handling contextual ambiguities and enhancing the accuracy of back-transliteration systems for Indian languages."
}