Abstract
We propose a character-based non-autoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has proven an efficient, parallelizable alternative to current encoder-decoder GEC systems. We show that word replacement edits may be suboptimal and lead to explosion of rules for spelling, diacritization and errors in morphologically rich languages, and propose a method for generating character transformations from GEC corpus. Finally, we train character transformation models for Czech, German and Russian, reaching solid results and dramatic speedup compared to autoregressive systems. The source code is released at https://github.com/ufal/wnut2021_character_transformations_gec.- Anthology ID:
- 2021.wnut-1.46
- Volume:
- Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 417–422
- Language:
- URL:
- https://aclanthology.org/2021.wnut-1.46
- DOI:
- 10.18653/v1/2021.wnut-1.46
- Cite (ACL):
- Milan Straka, Jakub Náplava, and Jana Straková. 2021. Character Transformations for Non-Autoregressive GEC Tagging. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 417–422, Online. Association for Computational Linguistics.
- Cite (Informal):
- Character Transformations for Non-Autoregressive GEC Tagging (Straka et al., WNUT 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.wnut-1.46.pdf
- Code
- ufal/wnut2021_character_transformations_gec
- Data
- AKCES-GEC, CoNLL-2014 Shared Task: Grammatical Error Correction