Skip to Main content Skip to Navigation
Theses

Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ?

Abstract : Recent advancements in the area of spoken language processing and the wide acceptance of portable devices, have attracted signicant interest in spoken dialogue systems.These conversational systems are man-machine interfaces which use natural language (speech) as the medium of interaction.In order to conduct dialogues, computers must have the ability to decide when and what information has to be exchanged with the users. The dialogue management module is responsible to make these decisions so that the intended task (such as ticket booking or appointment scheduling) can be achieved.Thus learning a good strategy for dialogue management is a critical task.In recent years reinforcement learning-based dialogue management optimization has evolved to be the state-of-the-art. A majority of the algorithms used for this purpose needs vast amounts of training data.However, data generation in the dialogue domain is an expensive and time consuming process. In order to cope with this and also to evaluatethe learnt dialogue strategies, user modelling in dialogue systems was introduced. These models simulate real users in order to generate synthetic data.Being computational models, they introduce some degree of modelling errors. In spite of this, system designers are forced to employ user models due to the data requirement of conventional reinforcement learning algorithms can learn optimal dialogue strategies from limited amount of training data when compared to the conventional algorithms. As a consequence of this, user models are no longer required for the purpose of optimization, yet they continue to provide a fast and easy means for quantifying the quality of dialogue strategies. Since existing methods for user modelling are relatively less realistic compared to real user behaviors, the focus is shifted towards user modelling by means of inverse reinforcement learning. Using experimental results, the proposed method's ability to learn a computational models with real user like qualities is showcased as part of this work.
Document type :
Theses
Complete list of metadatas

Cited literature [106 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00875229
Contributor : Abes Star :  Contact
Submitted on : Monday, October 21, 2013 - 2:42:08 PM
Last modification on : Tuesday, January 14, 2020 - 10:38:05 AM
Long-term archiving on: : Friday, April 7, 2017 - 2:06:18 PM

File

pdf2star-1381747338-these-chan...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-00875229, version 1

Collections

Citation

Senthilkumar Chandramohan. Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ?. Other [cs.OH]. Université d'Avignon, 2012. English. ⟨NNT : 2012AVIG0185⟩. ⟨tel-00875229⟩

Share

Metrics

Record views

544

Files downloads

732