An Extended Sequence Tagging Vocabulary for Grammatical Error Correction

Stuart Mesham, Christopher Bryant, Marek Rei, Zheng Yuan
2/12/2023
cs.CL

No official code found. Best implementation: wolfgarbe/SymSpell (3,463 stars, MIT, last commit 2026-04-21). 1 more below.

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.

View on arXivView PDF

Code Implementations(2)

wolfgarbe/SymSpellCommunity100%
MIT

SymSpell: 1 million times faster spelling correction & fuzzy search through Symmetric Delete spelling correction algorithm

3,463311C#, PythonMar 25, 20146 months agoMIT
approximate-string-matchingchinese-text-segmentationchinese-word-segmentationdamerau-levenshteinedit-distance+11 more
StuartMesham/gector_experiment_publicCommunity100%
Apache-2.0

Official repository for our EACL 2023 paper

81Shell, PythonOct 21, 20223 years agoApache-2.0

Cite this paper

@article{mesham2023extended,
  title  = {An Extended Sequence Tagging Vocabulary for Grammatical Error Correction},
  author = {Stuart Mesham and Christopher Bryant and Marek Rei and Zheng Yuan},
  year   = {2023},
  eprint = {2302.05913},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.05913v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.05913.svg)](https://codeofpaper.com/paper/2302.05913)

Discussion