Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems

Bo-Hsiang Tseng, Florian Kreyssig, Paweł Budzianowski, Iñigo Casanueva, Yen-Chen Wu, Stefan Ultes, Milica Gašić


Abstract
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey desired information. Traditional template-based generators can produce sentences with all necessary information, but these sentences are not sufficiently diverse. With RNN-based models, the diversity of the generated sentences can be high, however, in the process some information is lost. In this work, we improve an RNN-based generator by considering latent information at the sentence level during generation using conditional variational auto-encoder architecture. We demonstrate that our model outperforms the original RNN-based generator, while yielding highly diverse sentences. In addition, our model performs better when the training data is limited.
Anthology ID:
W18-5039
Volume:
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Kazunori Komatani, Diane Litman, Kai Yu, Alex Papangelis, Lawrence Cavedon, Mikio Nakano
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
338–343
Language:
URL:
https://aclanthology.org/W18-5039
DOI:
10.18653/v1/W18-5039
Bibkey:
Cite (ACL):
Bo-Hsiang Tseng, Florian Kreyssig, Paweł Budzianowski, Iñigo Casanueva, Yen-Chen Wu, Stefan Ultes, and Milica Gašić. 2018. Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 338–343, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems (Tseng et al., SIGDIAL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/W18-5039.pdf