User Simulation in Dialogue Systems using Inverse Reinforcement Learning

Abstract : Spoken Dialogue Systems (SDS) are man-machine interfaces which use natural language as the medium of interaction. Dialogue corpora collection for the purpose of training and evaluating dialogue systems is an expensive process. User simulators aim at simulating human users in order to generate synthetic data. Existing methods for user simulation mainly focus on generating data with the same statistical consistency as in some reference dialogue corpus. This paper outlines a novel approach for user simulation based on Inverse Reinforcement Learning (IRL). The task of building the user simulator is perceived as a task of imitation learning.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00652446
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, December 15, 2011 - 4:08:51 PM
Last modification on : Wednesday, July 31, 2019 - 4:18:03 PM
Long-term archiving on : Monday, December 5, 2016 - 10:56:27 AM

File

IS_2011_SCMGFLOP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00652446, version 1

Citation

Senthilkumar Chandramohan, Matthieu Geist, Fabrice Lefèvre, Olivier Pietquin. User Simulation in Dialogue Systems using Inverse Reinforcement Learning. Interspeech 2011, Aug 2011, Florence, Italy. pp.1025-1028. ⟨hal-00652446⟩

Share

Metrics

Record views

440

Files downloads

833