Grammatical error correction using hybrid systems and type filtering
Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task
Seventeenth Conference on Computational Natural Language Learning (CoNLL 2014): Shared Task
Association for Computational Linguistics
MetadataShow full item record
Felice, M., Yuan, Z., Andersen, Ø., Giannakoudaki, H. Y., & 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
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.
[We would like to thank] Cambridge English Language Assessment, a division of Cambridge Assessment, for supporting this research.
External link: http://www.aclweb.org/anthology/K/K14/#2014_1
This record's URL: https://www.repository.cam.ac.uk/handle/1810/267158