Latent Variable Dialogue Models and their Diversity

Kris Cao, Stephen Clark


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.
Anthology ID:
E17-2029
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
182–187
Language:
URL:
https://aclanthology.org/E17-2029
DOI:
Bibkey:
Cite (ACL):
Kris Cao and Stephen Clark. 2017. Latent Variable Dialogue Models and their Diversity. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 182–187, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Latent Variable Dialogue Models and their Diversity (Cao & Clark, EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/E17-2029.pdf