Show simple item record

dc.contributor.authorMrkšić, Nen
dc.contributor.authorVulić, Ien
dc.date.accessioned2018-11-14T00:31:01Z
dc.date.available2018-11-14T00:31:01Z
dc.date.issued2018-01-01en
dc.identifier.isbn9781948087346en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/285038
dc.description.abstractThis paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive manual retuning step whenever the model is deployed to a new dialogue domain. We show that this update mechanism can be learned jointly with the semantic decoding and context modelling parts of the NBT model, eliminating the last rule-based module from this DST framework. We propose two different statistical update mechanisms and show that dialogue dynamics can be modelled with a very small number of additional model parameters. In our DST evaluation over three languages, we show that this model achieves competitive performance and provides a robust framework for building resource-light DST models.
dc.titleFully statistical neural belief trackingen
dc.typeConference Object
prism.endingPage113
prism.publicationDate2018en
prism.publicationNameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)en
prism.startingPage108
prism.volume2en
dc.identifier.doi10.17863/CAM.32408
dcterms.dateAccepted2018-04-21en
rioxxterms.versionofrecord10.18653/v1/p18-2018en
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2018-01-01en
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648909)
rioxxterms.freetoread.startdate2019-07-10


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record