@inproceedings{sarawgi-etal-2026-digitizing,
    title = "Digitizing {N}epal{'}s Written Heritage: A Comprehensive {HTR} Pipeline for Old {N}epali Manuscripts",
    author = "Sarawgi, Anjali  and
      Garces Arias, Esteban  and
      Zotter, Christof",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.671/",
    pages = "14720--14746",
    ISBN = "979-8-89176-390-6",
    abstract = "This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9{\%}. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behavior and error patterns. Although the evaluation dataset is confidential, we release our training code, model configurations, and evaluation scripts to support further research on HTR for low-resource historical scripts."
}