Show simple item record

dc.contributor.authorKnill, KM
dc.contributor.authorGales, MJF
dc.contributor.authorManakul, PP
dc.contributor.authorCaines, AP
dc.date.accessioned2019-02-16T00:30:39Z
dc.date.accessioned2019-07-26T23:30:42Z
dc.date.available2019-02-16T00:30:39Z
dc.date.available2019-07-26T23:30:42Z
dc.date.issued2019
dc.identifier.issn1520-6149
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/295004
dc.description.abstractAutomatic language assessment and learning systems are required to support the global growth in English language learning. They need to be able to provide reliable and meaningful feedback to help learn- ers develop their skills. This paper considers the question of detect- ing “grammatical” errors in non-native spoken English as a first step to providing feedback on a learner’s use of the language. A state- of-the-art deep learning based grammatical error detection (GED) system designed for written texts is investigated on free speaking tasks across the full range of proficiency grades with a mix of first languages (L1s). This presents a number of challenges. Free speech contains disfluencies that disrupt the spoken language flow but are not grammatical errors. The lower the level of the learner the more these both will occur which makes the underlying task of automatic transcription harder. The baseline written GED system is seen to perform less well on manually transcribed spoken language. When the GED model is fine-tuned to free speech data from the target do- main the spoken system is able to match the written performance. Given the current state-of-the-art in ASR, however, and the ability to detect disfluencies grammatical error feedback from automated transcriptions remains a challenge.
dc.description.sponsorshipCambridge Assessment English
dc.publisherIEEE
dc.relation.replaceshttps://www.repository.cam.ac.uk/handle/1810/289493
dc.relation.replaces1810/289493
dc.subjectSpoken language assessment
dc.subjectCALL
dc.subjectgrammatical error detection
dc.titleAUTOMATIC GRAMMATICAL ERROR DETECTION OF NON-NATIVE SPOKEN LEARNER ENGLISH
dc.typeConference Object
prism.endingPage8131
prism.publicationDate2019
prism.publicationName2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
prism.startingPage8127
dc.identifier.doi10.17863/CAM.36743
dc.identifier.doi10.17863/CAM.42085
dcterms.dateAccepted2019-02-01
rioxxterms.versionofrecord10.1109/icassp.2019.8683755
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2019
dc.contributor.orcidKnill, Katherine [0000-0003-1292-2769]
dc.contributor.orcidGales, Mark [0000-0002-5311-8219]
dc.contributor.orcidCaines, Andrew [0000-0001-9647-4902]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idCambridge Assessment (unknown)
pubs.conference-nameICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
pubs.conference-start-date2019-05-12
cam.orpheus.successThu Nov 05 11:54:23 GMT 2020 - Embargo updated
pubs.conference-finish-date2019-05-17
rioxxterms.freetoread.startdate2020-12-31


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record