Latent Variable Dialogue Models and their Diversity
Published version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Clark, SC
Abstract
We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the ‘boring output’ issue of deterministic dialogue models. Experiments show that our model generates more diverse outputs than baseline models, and also generates more consistently acceptable output than sampling from a deterministic encoder-decoder model.
Description
Keywords
Journal Title
15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017)
Conference Name
Journal ISSN
Volume Title
Publisher
Publisher DOI
Publisher URL
Sponsorship
EPSRC (1510349)