CUED Publications database

A network-based end-to-end trainable task-oriented dialogue system

Wen, TH and Vandyke, D and Mrkšíc, N and Gašíc, M and Rojas-Barahona, LM and Su, PH and Ultes, S and Young, S (2017) A network-based end-to-end trainable task-oriented dialogue system. In: UNSPECIFIED pp. 438-449..

Full text not available from this repository.

Abstract

© 2017 Association for Computational Linguistics. Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing taskoriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, textout end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: cs.CL cs.CL cs.AI cs.NE stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 20:02
Last Modified: 12 Oct 2017 01:48
DOI: