Show simple item record

dc.contributor.authorKhan, Kashif
dc.date.accessioned2020-08-28 17:43:25 (GMT)
dc.date.available2020-08-28 17:43:25 (GMT)
dc.date.issued2020-08-28
dc.date.submitted2020-08-24
dc.identifier.urihttp://hdl.handle.net/10012/16188
dc.description.abstractDialog response generation is the task of generating response utterance given a query utterance. Apart from generating relevant and coherent responses, one would like the dialog generation model to generate diverse and informative sentences. In this work, we propose and explore a novel multi-stage dialog response generation approach. In the first stage of our proposed multi-stage approach, we construct a variational latent space on the bag-of-words representation of the query and response utterances. In the second stage, transformation from query latent code to response latent code is learned using an adversarial process. The final stage involves fine-tuning a pretrained transformer based model called text-to-text transfer (T5) (Raffel et al., 2019) using a novel training regimen to generate the response utterances by conditioning on the query utterance and the response word learned in the previous stage. We evaluate our proposed approach on two popular dialog datasets. Our proposed approach outperforms the baseline transformer model on multiple quantitative metrics including overlap metric (Bleu), diversity metrics (distinct-1 and distinct-2), and fluency metric (perplexity).en
dc.language.isoenen
dc.publisherUniversity of Waterlooen
dc.subjectnatural language generationen
dc.subjectdialog response generationen
dc.titleDialog Response Generation Using Adversarially Learned Latent Bag-of-Wordsen
dc.typeMaster Thesisen
dc.pendingfalse
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws.contributor.advisorVechtomova, Olga
uws.contributor.affiliation1Faculty of Mathematicsen
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.typeOfResourceTexten
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record


UWSpace

University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages