Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 882

The DOI matches its Crossref record; 111 of the 111 references it cites were found in a registry or an index.

POMDP-Based Statistical Spoken Dialog Systems: A Review

Young, Steve, Gasic, Milica, Thomson, Blaise, Williams, Jason D.·2013·Proceedings of the IEEE

Abstract

Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jproc.2012.2225812

Cites

111 of 111 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 50

  1. 10.3115/1075096.1075127 · doi:10.3115/1075096.1075127
  2. bohus, 2006, A ‘K hypotheses + other’ belief updating model, Proc AAAI Workshop Statist Empirical Approaches Spoken Dialogue Syst, 13
  3. crook, 2011, Lossless value directed compression of complex user goal states for statistical spoken dialogue systems, Proc Annu Conf Int Speech Commun Assoc, 1029
  4. 10.1109/SLT.2010.5700896 · doi:10.1109/slt.2010.5700896
  5. 10.1109/ICASSP.2008.4518765 · doi:10.1109/icassp.2008.4518765
  6. 10.3115/1557690.1557710 · doi:10.3115/1557690.1557710
  7. gai, 2011, Effective handling of dialogue state in the hidden information state POMDP dialogue manager, ACM Trans Speech Lang Process, 7
  8. thomson, 2008, Evaluating semantic-level confidence scores with multiple hypotheses, Proc Annu Conf Int Speech Commun Assoc, 1153
  9. 10.1109/ICASSP.2007.367189 · doi:10.1109/icassp.2007.367189
  10. 10.1007/978-3-540-30211-7_1 · doi:10.1007/978-3-540-30211-7_1
  11. 10.3115/1220835.1220870 · doi:10.3115/1220835.1220870
  12. tetreault, 2006, Using reinforcement learning to build a better model of dialogue state, Proc of the Association for Computational Linguistics
  13. 10.1007/978-3-642-21043-3_11 · doi:10.1007/978-3-642-21043-3_11
  14. pinault, 2011, Unsupervised clustering of probability distributions of semantic frame graphs for pomdp-based spoken dialogue systems with summary space, Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI
  15. pinault, 2011, Semantic graph clustering for POMDP-based spoken dialog systems, Proc Annu Conf Int Speech Commun Assoc, 1321
  16. boularias, 2010, Learning the reward model of dialogue POMDPs from data, Proc NIPS Workshop of Mach Learn for Assistive Tech
  17. pinault, 2009, Feature-based summary space for stochastic dialogue modeling with hierarchical semantic frames, Proc Annu Conf Int Speech Commun Assoc, 284
  18. bui, 2007, Practical dialogue manager development using POMDPs, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 215
  19. 10.1109/SLT.2006.326775 · doi:10.1109/slt.2006.326775
  20. cuayhuitl, 2006, Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces, Proc Annu Conf Int Speech Commun Assoc, 547
  21. lison, 2010, Towards relational POMDPs for adaptive dialogue management, Proc Annu Meeting Assoc Comput Linguist, 7
  22. williams, 2011, An empirical evaluation of a statistical dialog system in public use, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 130
  23. 10.3115/1556328.1556329 · doi:10.3115/1556328.1556329
  24. 10.1016/j.specom.2008.05.007 · doi:10.1016/j.specom.2008.05.007
  25. schatzmann, 2008, Statistical User and Error Modelling for Spoken Dialogue Systems
  26. gai, 2009, Back-off action selection in summary space-based POMDP dialogue systems, Proc IEEE Workshop Autom Speech Recog and Understanding, 456
  27. 10.3115/1622064.1622097 · doi:10.3115/1622064.1622097
  28. mcgraw, 2010, Collecting voices from the cloud, Proc Int Conf Lang Resources Eval, 1576
  29. williams, 2008, Integrating expert knowledge into POMDP optimization for spoken dialog systems, Proc AAAI Workshop Adv POMDP Solvers
  30. 10.1109/ICASSP.2011.5947627 · doi:10.1109/icassp.2011.5947627
  31. lefevre, 2009, <ref_formula><tex Notation="TeX">$k$</tex></ref_formula>-nearest neighbor Monte-Carlo control algorithm for POMDP-based dialogue systems, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue
  32. 10.1109/SLT.2010.5700863 · doi:10.1109/slt.2010.5700863
  33. 10.1109/ICASSP.2002.1005671 · doi:10.1109/icassp.2002.1005671
  34. chandramohan, 2011, User simulation in dialogue systems using inverse reinforcement learning, Proc Annu Conf Int Speech Commun Assoc, 1025
  35. 10.3115/1557690.1557722 · doi:10.3115/1557690.1557722
  36. 10.1016/j.csl.2009.03.002 · doi:10.1016/j.csl.2009.03.002
  37. 10.1109/SLT.2008.4777855 · doi:10.1109/slt.2008.4777855
  38. rossignol, 2011, Training a BN-based user model for dialogue simulation with missing data, Proc Int Joint Conf Natural Lang Process, 598
  39. 10.1109/TSA.2005.855836 · DOI
  40. hua ai, 2007, Comparing user simulation models for dialog strategy learning, Proc Conf North Amer Chapt Assoc Comput Linguist, 1
  41. 10.1109/ASRU.2007.4430167 · doi:10.1109/asru.2007.4430167
  42. 10.1007/978-3-540-74628-7_74 · doi:10.1007/978-3-540-74628-7_74
  43. littman, 2002, Advances in Neural Information Processing Systems 14, 1555
  44. smith, 2005, Point-based POMDP algorithms: Improved analysis and implementation, Proc 13th Annu Conf Uncertainty Artif Intell, 542
  45. gai, 2011, Statistical Dialogue Modelling
  46. gai, 2010, Gaussian processes for fast policy optimisation of a POMDP dialogue manager for a real-world task, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 201
  47. pietquin, 2011, Sample efficient on-line learning of optimal dialogue policies with Kalman temporal differences, Proc Int Joint Conf Artif Intell, 1878
  48. janarthanam, 2011, ‘The day after the day after tomorrow?’ A machine learning approach to adaptive temporal expression generation: Training and evaluation with real users, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 142
  49. kim, 2007, Multimodal dialog system using hidden information state dialog manager, Proc Int Conf Multimodal Interfaces Demonstration Session
  50. pietquin, 2004, A Framework for Unsupervised Learning of Dialogue Strategies

Cited by

See all 882

Metadata

Authors
Young, S., Gasic, M., Thomson, B., & Williams, J. D.
Venue
Proceedings of the IEEE
Published
2013-05
Volume
101
Issue
5
Pages
1160-1179
ISSN
  • 0018-9219 (ISSN-L)
  • 1558-2256
OpenAlex
W1975244201
Cited by
882
References
111
FWCI
48.96
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.