Czech Grammar Error Correction with a Large and Diverse Corpus

Jakub Náplava, Milan Straka, Jana Straková, Alexandr Rosen


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 http://hdl.handle.net/11234/1-4639.
Anthology ID:
2022.tacl-1.26
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
452–467
Language:
URL:
https://aclanthology.org/2022.tacl-1.26
DOI:
10.1162/tacl_a_00470
Bibkey:
Cite (ACL):
Jakub Náplava, Milan Straka, Jana Straková, and Alexandr Rosen. 2022. Czech Grammar Error Correction with a Large and Diverse Corpus. Transactions of the Association for Computational Linguistics, 10:452–467.
Cite (Informal):
Czech Grammar Error Correction with a Large and Diverse Corpus (Náplava et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.26.pdf
Video:
 https://aclanthology.org/2022.tacl-1.26.mp4