@inproceedings{butt-etal-2025-low,
    title = "Low-Resource Transliteration for {R}oman-{U}rdu and {U}rdu Using Transformer-Based Models",
    author = {Butt, Umer  and
      Varanasi, Stalin  and
      Neumann, G{\"u}nter},
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-hong  and
      Vylomova, Ekaterina  and
      Pirinen, Flammie  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, U.S.A.",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.loresmt-1.13/",
    pages = "144--153",
    ISBN = "979-8-89176-230-5",
    abstract = "As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. Transliteration between Urdu and its Romanized form, Roman Urdu, remains underexplored despite the widespread use of both scripts in South Asia. Prior work using RNNs on the Roman-Urdu-Parl dataset showed promising results but suffered from poor domain adaptability and limited evaluation. We propose a transformer-based approach using the m2m100 multilingual translation model, enhanced with masked language modeling (MLM) pretraining and fine-tuning on both Roman-Urdu-Parl and the domain diverse Dakshina dataset. To address previous evaluation flaws, we introduce rigorous dataset splits and assess performance using BLEU, character-level BLEU, and CHRF. Our model achieves strong transliteration performance, with Char-BLEU scores of 96.37 for Urdu{\textrightarrow}Roman-Urdu and 97.44 for Roman-Urdu{\textrightarrow}Urdu. These results outperform both RNN baselines and GPT-4o Mini and demonstrate the effectiveness of multilingual transfer learning for low-resource transliteration tasks."
}