Show simple item record

dc.contributor.authorMalinin, Andreyen
dc.contributor.authorRagni, Antonen
dc.contributor.authorKnill, Katherineen
dc.contributor.authorGales, Marken
dc.date.accessioned2018-09-05T11:07:51Z
dc.date.available2018-09-05T11:07:51Z
dc.date.issued2017-01-01en
dc.identifier.isbn9781945626760en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/279180
dc.description.abstractThere is a growing demand for automatic assessment of spoken English proficiency. These systems need to handle large vari- ations in input data owing to the wide range of candidate skill levels and L1s, and errors from ASR. Some candidates will be a poor match to the training data set, undermining the validity of the predicted grade. For high stakes tests it is essen- tial for such systems not only to grade well, but also to provide a measure of their uncertainty in their predictions, en- abling rejection to human graders. Pre- vious work examined Gaussian Process (GP) graders which, though successful, do not scale well with large data sets. Deep Neural Networks (DNN) may also be used to provide uncertainty using Monte-Carlo Dropout (MCD). This paper proposes a novel method to yield uncertainty and compares it to GPs and DNNs with MCD. The proposed approach explicitly teaches a DNN to have low uncertainty on train- ing data and high uncertainty on generated artificial data. On experiments conducted on data from the Business Language Test- ing Service (BULATS), the proposed ap- proach is found to outperform GPs and DNNs with MCD in uncertainty-based re- jection whilst achieving comparable grad- ing performance.
dc.publisherAssociation for Computational Linguistics
dc.titleIncorporating uncertainty into deep learning for spoken language assessmenten
dc.typeConference Object
prism.endingPage50
prism.publicationDate2017en
prism.publicationNameACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)en
prism.startingPage45
prism.volume2en
dc.identifier.doi10.17863/CAM.26560
dcterms.dateAccepted2017-03-31en
rioxxterms.versionofrecord10.18653/v1/P17-2008en
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-01-01en
dc.contributor.orcidKnill, Katherine [0000-0003-1292-2769]
dc.contributor.orcidGales, Mark [0000-0002-5311-8219]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idEPSRC (1464018)
pubs.funder-project-idCambridge Assessment (unknown)
rioxxterms.freetoread.startdate2018-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record