Abstract
We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms. Our approach improves generalisation: the proposed new tagset allows a smaller number of tags to correct a larger range of errors. Our results show a performance improvement both overall and in the targeted error categories. We further show that ensembles trained with our new tagset outperform those trained with the baseline tagset on the public BEA benchmark.- Anthology ID:
- 2023.findings-eacl.119
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1608–1619
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.119
- DOI:
- 10.18653/v1/2023.findings-eacl.119
- Cite (ACL):
- Stuart Mesham, Christopher Bryant, Marek Rei, and Zheng Yuan. 2023. An Extended Sequence Tagging Vocabulary for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1608–1619, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- An Extended Sequence Tagging Vocabulary for Grammatical Error Correction (Mesham et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-eacl.119.pdf