@inproceedings{moon-okazaki-2020-jamo,
    title = "Jamo Pair Encoding: Subcharacter Representation-based Extreme {K}orean Vocabulary Compression for Efficient Subword Tokenization",
    author = "Moon, Sangwhan  and
      Okazaki, Naoaki",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.lrec-1.429/",
    pages = "3490--3497",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "In the context of multilingual language model pre-training, vocabulary size for languages with a broad set of potential characters is an unsolved problem. We propose two algorithms applicable in any unsupervised multilingual pre-training task, increasing the elasticity of budget required for building the vocabulary in Byte-Pair Encoding inspired tokenizers, significantly reducing the cost of supporting Korean in a multilingual model."
}