Show simple item record

dc.contributor.authorFelice, Men
dc.contributor.authorYuan, Zen
dc.contributor.authorAndersen, ØEen
dc.contributor.authorGiannakoudaki, Helen Yannakoudakisen
dc.contributor.authorKochmar, Ekaterinaen
dc.contributor.editorNg, HTen
dc.contributor.editorWu, SMen
dc.contributor.editorBriscoe, Ten
dc.contributor.editorHadiwinoto, Cen
dc.contributor.editorSusanto, RHen
dc.contributor.editorBryant, Cen
dc.date.accessioned2017-09-12T09:02:50Z
dc.date.available2017-09-12T09:02:50Z
dc.date.issued2014en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/267158
dc.description.abstractThis 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.
dc.description.sponsorship[We would like to thank] Cambridge English Language Assessment, a division of Cambridge Assessment, for supporting this research.
dc.language.isoenen
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 Internationalen
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en
dc.titleGrammatical error correction using hybrid systems and type filteringen
dc.typeConference Object
prism.endingPage24
prism.publicationDate2014en
prism.publicationNameProceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Tasken
prism.startingPage15
dc.identifier.doi10.17863/CAM.13173
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en
rioxxterms.licenseref.startdate2014en
dc.contributor.orcidGiannakoudaki, Helen Yannakoudakis [0000-0002-4429-7729]
rioxxterms.typeConference Paper/Proceeding/Abstracten
dc.identifier.urlhttp://www.aclweb.org/anthology/K/K14/#2014_1en
pubs.conference-nameSeventeenth Conference on Computational Natural Language Learning (CoNLL 2014): Shared Tasken
pubs.conference-start-date2014-07-26en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 4.0 International
Except where otherwise noted, this item's licence is described as Attribution-NonCommercial-ShareAlike 4.0 International