@inproceedings{lee-etal-2025-jamo,
    title = "Jamo-Level Subword Tokenization in Low-Resource {K}orean Machine Translation",
    author = "Lee, Junyoung  and
      Cognetta, Marco  and
      Moon, Sangwhan  and
      Okazaki, Naoaki",
    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/Ingest-2025-COMPUTEL/2025.loresmt-1.8/",
    pages = "66--80",
    ISBN = "979-8-89176-230-5",
    abstract = "Subword tokenization, where text is represented in an intermediate form between full words and characters, is ubiquitous in modern NLP due to its ability to represent any input sentence with a small vocabulary. However for Korean, where there are 11,172 base characters (*syllables*) in its alphabet, it is difficult to have a vocabulary large enough to succinctly encode text while fitting within parameter-budget constraints. This motivates us to explore an alternative representation for Korean which relies on the decompositional nature of Korean syllables: a syllable can be uniquely decomposed into a sequence of two or three subcharacters (*jamo*), of which there are only 68.Using jamo as the basis for subword tokenization (e.g., byte-pair encoding) leads to shorter tokenized sequences with fewer vocabulary parameters, exposes the model to sub-syllable-level morphological information, and increases the amount of augmentation gained from subword regularization. We evaluate jamo-level subword tokenization on several Korean translation tasks and find that jamo-level subword models consistently outperform syllable- and byte-level models in low-resource and restricted-vocabulary settings."
}