@inproceedings{higashiyama-utiyama-2025-comprehensive,
    title = "Comprehensive Evaluation on Lexical Normalization: Boundary-Aware Approaches for Unsegmented Languages",
    author = "Higashiyama, Shohei  and
      Utiyama, Masao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.684/",
    doi = "10.18653/v1/2025.findings-emnlp.684",
    pages = "12774--12799",
    ISBN = "979-8-89176-335-7",
    abstract = "Lexical normalization research has sought to tackle the challenge of processing informal expressions in user-generated text, yet the absence of comprehensive evaluations leaves it unclear which methods excel across multiple perspectives. Focusing on unsegmented languages, we make three key contributions: (1) creating a large-scale, multi-domain Japanese normalization dataset, (2) developing normalization methods based on state-of-the-art pre-trained models, and (3) conducting experiments across multiple evaluation perspectives. Our experiments show that both encoder-only and decoder-only approaches achieve promising results in both accuracy and efficiency."
}