Zero-Shot Dialog Generation with Cross-Domain Latent Actions

Tiancheng Zhao, Maxine Eskenazi


Abstract
This paper introduces zero-shot dialog generation (ZSDG), as a step towards neural dialog systems that can instantly generalize to new situations with minimum data. ZSDG requires an end-to-end generative dialog system to generalize to a new domain for which only a domain description is provided and no training dialogs are available. Then a novel learning framework, Action Matching, is proposed. This algorithm can learn a cross-domain embedding space that models the semantics of dialog responses which in turn, enables a neural dialog generation model to generalize to new domains. We evaluate our methods on two datasets, a new synthetic dialog dataset, and an existing human-human multi-domain dialog dataset. Experimental results show that our method is able to achieve superior performance in learning dialog models that can rapidly adapt their behavior to new domains and suggests promising future research.
Anthology ID:
W18-5001
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:
1–10
Language:
URL:
https://aclanthology.org/W18-5001
DOI:
10.18653/v1/W18-5001
Bibkey:
Cite (ACL):
Tiancheng Zhao and Maxine Eskenazi. 2018. Zero-Shot Dialog Generation with Cross-Domain Latent Actions. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 1–10, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Dialog Generation with Cross-Domain Latent Actions (Zhao & Eskenazi, SIGDIAL 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5001.pdf
Code
 snakeztc/NeuralDialog-ZSDG +  additional community code