Effects of user modeling on POMDP-based dialogue systems

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 809
  • Download : 468
Partially observable Markov decision processes (POMDPs) have gained signicant interest in research on spoken dialogue systems, due to among many benets its ability to naturally model the dialogue strategy selection problem under the unreliability in automated speech recognition. However, the POMDP approaches are essentially model-based, and as a result, the dialogue strategy computed from POMDP is subject to the correctness of the model. In this paper, we extend some of the previous user models for POMDPs, and evaluate the effects of user models on the dialogue strategy computed from POMDP.
Publisher
Interspeech
Issue Date
2008-09-22
Language
English
Citation

9th Annual Conference of the International Speech Communication Association, 2008, pp.1169 - 1172

URI
http://hdl.handle.net/10203/17392
Appears in Collection
AI-Conference Papers(학술대회논문)CS-Conference Papers(학술회의논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0