Grammatical error correction using hybrid systems and type filtering
View / Open Files
Authors
Felice, M
Yuan, Z
Andersen, ØE
Yannakoudakis, H
Kochmar, Ekaterina
Editors
Ng, HT
Wu, SM
Briscoe, T
Hadiwinoto, C
Susanto, RH
Bryant, C
Publication Date
2014Journal Title
Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task
Conference Name
Seventeenth Conference on Computational Natural Language Learning (CoNLL 2014): Shared Task
Publisher
Association for Computational Linguistics
Pages
15-24
Language
English
Type
Conference Object
This Version
VoR
Metadata
Show full item recordCitation
Felice, M., Yuan, Z., Andersen, Ø., Yannakoudakis, H., & Kochmar, E. (2014). Grammatical error correction using hybrid systems and type filtering. Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task, 15-24. http://www.aclweb.org/anthology/K/K14/#2014_1
Abstract
This paper describes our submission to the CoNLL 2014 shared task on grammatical error correction using a hybrid approach, which includes both a rule-based and an SMT system augmented by a large webbased
language model. Furthermore, we demonstrate that correction type estimation can be used to remove unnecessary corrections, improving precision without harming recall. Our best hybrid system achieves state of-the-art results, ranking first on the original test set and second on the test set with alternative annotations.
Sponsorship
[We would like to thank] Cambridge English Language Assessment, a division of Cambridge Assessment, for supporting this research.
Identifiers
External link: http://www.aclweb.org/anthology/K/K14/#2014_1
This record's URL: https://www.repository.cam.ac.uk/handle/1810/267158
Rights
Attribution-NonCommercial-ShareAlike 4.0 International, Attribution-NonCommercial-ShareAlike 4.0 International