Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/154469
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXu, H.en_US
dc.contributor.authorPeng, Haiyunen_US
dc.contributor.authorXie, H.en_US
dc.contributor.authorCambria, Eriken_US
dc.contributor.authorZhou, L.en_US
dc.contributor.authorZheng, W.en_US
dc.date.accessioned2021-12-23T04:45:33Z-
dc.date.available2021-12-23T04:45:33Z-
dc.date.issued2020-
dc.identifier.citationXu, H., Peng, H., Xie, H., Cambria, E., Zhou, L. & Zheng, W. (2020). End-to-end latent-variable task-oriented dialogue system with exact log-likelihood optimization. World Wide Web, 23, 1989-2002. https://dx.doi.org/10.1007/s11280-019-00688-8en_US
dc.identifier.issn1386-145Xen_US
dc.identifier.urihttps://hdl.handle.net/10356/154469-
dc.description.abstractWe propose an end-to-end dialogue model based on a hierarchical encoder-decoder, which employed a discrete latent variable to learn underlying dialogue intentions. The system is able to model the structure of utterances dominated by statistics of the language and the dependencies among utterances in dialogues without manual dialogue state design. We argue that the latent discrete variable interprets the intentions that guide machine responses generation. We also propose a model which can be refined autonomously with reinforcement learning, due to that intention selection at each dialogue turn can be formulated as a sequential decision-making process. Our experiments show that exact MLE optimized model is much more robust than neural variational inference on dialogue success rate with limited BLEU sacrifice.en_US
dc.language.isoenen_US
dc.relation.ispartofWorld Wide Weben_US
dc.rights© 2019 Springer Science+Business Media, LLC, part of Springer Nature. All rights reserved.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleEnd-to-end latent-variable task-oriented dialogue system with exact log-likelihood optimizationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.identifier.doi10.1007/s11280-019-00688-8-
dc.identifier.scopus2-s2.0-85067260059-
dc.identifier.volume23en_US
dc.identifier.spage1989en_US
dc.identifier.epage2002en_US
dc.subject.keywordsDialogue Modelen_US
dc.subject.keywordsHierarchical Encoder-Decoderen_US
dc.description.acknowledgementThis work was supported by the Shenzhen Science and Technology Innovation Committee with the project name of Intelligent Question Answering Robot, under grant NO. CKCY20170508121036342.en_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:SCSE Journal Articles

Page view(s)

25
Updated on May 27, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.