Show simple item record

dc.contributor.authorGiannakoudaki, E
dc.contributor.authorRei, M
dc.contributor.authorAndersen, OE
dc.contributor.authorYuan, Zheng
dc.contributor.editorMartha, P
dc.contributor.editorRebecca, H
dc.contributor.editorSebastian, R
dc.date.accessioned2019-08-13T09:57:37Z
dc.date.available2019-08-13T09:57:37Z
dc.date.issued2017-09-30
dc.identifier.isbn9781945626838
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/295717
dc.description.abstractWe propose an approach to N-best list reranking using neural sequence-labelling models. We train a compositional model for error detection that calculates the probability of each token in a sentence being correct or incorrect, utilising the full sentence as context. Using the error detection model, we then re-rank the N best hypotheses generated by statistical machine translation systems. Our approach achieves state-of-the-art results on error correction for three different datasets, and it has the additional advantage of only using a small set of easily computed features that require no linguistic input.
dc.languageEnglish
dc.language.isoen
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.titleNeural Sequence-Labelling Models for Grammatical Error Correction
dc.typeConference Object
prism.endingPage2806
prism.numberD17-1297
prism.publicationDate2017
prism.publicationNameProceedings of the 2017 Conference on Empirical Methods in natural Language Processing
prism.startingPage2795
prism.volumeD17-1
dc.identifier.doi10.17863/CAM.21371
dcterms.dateAccepted2017-07-01
rioxxterms.versionofrecord10.18653/v1/D17-1297
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
rioxxterms.licenseref.startdate2017-09-30
dc.contributor.orcidYannakoudakis, Helen [0000-0002-4429-7729]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idCambridge Assessment (unknown)
pubs.conference-nameConference on Empirical Methods in Natural Language Processing
pubs.conference-start-date2017-09-07
cam.orpheus.successThu Nov 05 11:54:30 GMT 2020 - The item has an open VoR version.
pubs.conference-finish-date2017-09-11
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

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