@inproceedings{sung-shin-2023-towards,
    title = "Towards {L}2-friendly pipelines for learner corpora: A case of written production by {L}2-{K}orean learners",
    author = "Sung, Hakyung  and
      Shin, Gyu-Ho",
    editor = {Kochmar, Ekaterina  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Madnani, Nitin  and
      Tack, Ana{\"i}s  and
      Yaneva, Victoria  and
      Yuan, Zheng  and
      Zesch, Torsten},
    booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.bea-1.6/",
    doi = "10.18653/v1/2023.bea-1.6",
    pages = "72--82",
    abstract = "We introduce the Korean-Learner-Morpheme (KLM) corpus, a manually annotated dataset consisting of 129,784 morphemes from second language (L2) learners of Korean, featuring morpheme tokenization and part-of-speech (POS) tagging. We evaluate the performance of four Korean morphological analyzers in tokenization and POS tagging on the L2- Korean corpus. Results highlight the analyzers' reduced performance on L2 data, indicating the limitation of advanced deep-learning models when dealing with L2-Korean corpora. We further show that fine-tuning one of the models with the KLM corpus improves its accuracy of tokenization and POS tagging on L2-Korean dataset."
}