Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1868
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/P17-1074
- Title of conference / published proceedings
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics
- First page
- 793
- Volume
- 1
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2017
- 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
-
2
- Research group(s)
-
-
- Citation count
- 23
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Automatic evaluation of grammatical error correction (GEC) systems relies on mappings between manually corrected versions of sentences containing errors. Most algorithms are unable to identify different types of error and so support improvement. This paper presented the first automatic comprehensive and consistent method of mapping such sentence pairs and typing the errors. It is well cited because most subsequent work on GEC has used the open source code released to type errors during system training and testing, and it was adopted as the standard in the 2019 BEA shared task on GEC.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -