@inproceedings{hasan-etal-2025-gradet,
    title = "{G}ra{D}e{T}-{HTR}: A Resource-Efficient {B}engali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer",
    author = "Hasan, Md. Mahmudul  and
      Choudhury, Ahmed Nesar Tahsin  and
      Hasan, Mahmudul  and
      Khan, Md Mosaddek",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.52/",
    pages = "696--706",
    ISBN = "979-8-89176-334-0",
    abstract = "Despite Bengali being the sixth most spoken language in the world, handwritten text recognition (HTR) systems for Bengali remain severely underdeveloped. The complexity of Bengali script{---}featuring conjuncts, diacritics, and highly variable handwriting styles{---}combined with a scarcity of annotated datasets makes this task particularly challenging. We present **GraDeT-HTR**, a resource-efficient Bengali handwritten text recognition system based on a **Gra**pheme-aware **De**coder-only **T**ransformer architecture. To address the unique challenges of Bengali script, we augment the performance of a decoder-only transformer by integrating a grapheme-based tokenizer and demonstrate that it significantly improves recognition accuracy compared to conventional subword tokenizers. Our model is pretrained on large-scale synthetic data and fine-tuned on real human-annotated samples, achieving state-of-the-art performance on multiple benchmark datasets."
}