Grammatical error correction using neural machine translation
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1904
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/n16-1042
- Title of conference / published proceedings
- 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
- First page
- 380
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- January
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This was the first paper to apply a neural machine translation, as opposed to statistical machine translation, model to the task of translating 'bad' English produced by learners of English as a further language into 'good' grammatical and idiomatic English. (See e.g. Neural network translation models for grammatical error correction, Chollampatt et al., 2016, IJCAI, https://arxiv.org/abs/1606.00189 for independent corroboration.) As such it is well cited and directly influenced nearly all subsequent work on GEC so that, for example, in the 2019 shared task on GEC (Bryant et al., 2019, BEA, https://www.aclweb.org/anthology/W19-4406.pdf) *all* participants adapted NMT-based modles to the task.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -