@inproceedings{oda-2023-training,
    title = "Training for Grammatical Error Correction Without Human-Annotated {L}2 Learners' Corpora",
    author = "Oda, Mikio",
    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/ingest-emnlp/2023.bea-1.38/",
    doi = "10.18653/v1/2023.bea-1.38",
    pages = "455--465",
    abstract = "Grammatical error correction (GEC) is a challenging task for non-native second language (L2) learners and learning machines. Data-driven GEC learning requires as much human-annotated genuine training data as possible. However, it is difficult to produce larger-scale human-annotated data, and synthetically generated large-scale parallel training data is valuable for GEC systems. In this paper, we propose a method for rebuilding a corpus of synthetic parallel data using target sentences predicted by a GEC model to improve performance. Experimental results show that our proposed pre-training outperforms that on the original synthetic datasets. Moreover, it is also shown that our proposed training without human-annotated L2 learners' corpora is as practical as conventional full pipeline training with both synthetic datasets and L2 learners' corpora in terms of accuracy."
}