@article{naplava-etal-2022-czech,
    title = "{C}zech Grammar Error Correction with a Large and Diverse Corpus",
    author = "N{\'a}plava, Jakub  and
      Straka, Milan  and
      Strakov{\'a}, Jana  and
      Rosen, Alexandr",
    editor = "Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "10",
    year = "2022",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.tacl-1.26/",
    doi = "10.1162/tacl_a_00470",
    pages = "452--467",
    abstract = "We introduce a large and diverse Czech corpus annotated for grammatical error correction (GEC) with the aim to contribute to the still scarce data resources in this domain for languages other than English. The Grammar Error Correction Corpus for Czech (GECCC) offers a variety of four domains, covering error distributions ranging from high error density essays written by non-native speakers, to website texts, where errors are expected to be much less common. We compare several Czech GEC systems, including several Transformer-based ones, setting a strong baseline to future research. Finally, we meta-evaluate common GEC metrics against human judgments on our data. We make the new Czech GEC corpus publicly available under the CC BY-SA 4.0 license at \url{http://hdl.handle.net/11234/1-4639}."
}