Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks

Jason D. Williams, Lars Liden


Abstract
This is a demonstration of interactive teaching for practical end-to-end dialog systems driven by a recurrent neural network. In this approach, a developer teaches the network by interacting with the system and providing on-the-spot corrections. Once a system is deployed, a developer can also correct mistakes in logged dialogs. This demonstration shows both of these teaching methods applied to dialog systems in three domains: pizza ordering, restaurant information, and weather forecasts.
Anthology ID:
W17-5511
Volume:
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
Month:
August
Year:
2017
Address:
Saarbrücken, Germany
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
82–85
Language:
URL:
https://aclanthology.org/W17-5511
DOI:
10.18653/v1/W17-5511
Bibkey:
Cite (ACL):
Jason D. Williams and Lars Liden. 2017. Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 82–85, Saarbrücken, Germany. Association for Computational Linguistics.
Cite (Informal):
Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks (Williams & Liden, SIGDIAL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W17-5511.pdf