CoChat

The Hidden Agenda User Simulation Model

Schatzmann, Jost, Young, Steve · 2009 · IEEE Transactions on Audio, Speech, and Language Processing
Cited by 94

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

A key advantage of taking a statistical approach to spoken dialogue systems is the ability to formalise dialogue policy design as a stochastic optimization problem. However, since dialogue policies are learnt by interactively exploring alternative dialogue paths, conventional static dialogue corpora cannot be used directly for training and instead, a user simulator is commonly used. This paper describes a novel statistical user model based on a compact stack-like state representation called auseragendawhich allows state transitions to be modeled as sequences of push- and pop-operations and elegantly encodes the dialogue history from a user's point of view. An expectation-maximisation based algorithm is presented which models the observable user output in terms of a sequence of hidden states and thereby allows the model to be trained on a corpus of minimally annotated data. Experimental results with a real-world dialogue system demonstrate that the trained user model can be successfully used to optimise a dialogue policy which outperforms a hand-crafted baseline in terms of task completion rates and user satisfaction scores.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/tasl.2008.2012071

Cites

3 of 3 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Show all 3 references

Research works printed but not linked: 36

  1. 10.1109/ASRU.2007.4430164 · doi:10.1109/asru.2007.4430164
  2. 10.3115/990820.990893 · DOI · Paper page
  3. schatzmann, 2005, effects of the user model on simulation-based learning of dialogue strategies, Proc ASRU
  4. schatzmann, 2008, Statistical user and error modeling for spoken dialogue systems
  5. 10.1109/ICSLP.1996.607774 · DOI
  6. 10.1109/ICASSP.2007.367185 · DOI
  7. issar, 1994, flexible parsing: cmu's approach to spoken language understanding, Proc ARPA Workshop Spoken Lang Technol
  8. 10.3115/1075812.1075857 · DOI · Paper page
  9. lemon, 2007, dialogue policy learning for combinations of noise and user simulation: transfer results, Proc SIGDial
  10. 10.3115/1614108.1614146 · DOI · Paper page
  11. pietquin, 2004, A Framework for Unsupervised Learning of Dialogue Strategies
  12. georgila, 2005, learning user simulations for information state update dialog systems, Proc EUROSPEECH
  13. frampton, 2006, learning more effective dialogue strategies using limited dialogue move features, Proc ACL
  14. lemon, 2006, evaluating effectiveness and portability of reinforcement learned dialogue strategies with real users: the talk towninfo eval, Proc SLT
  15. rieser, 2006, cluster-based user simulations for learning dialogue strategies, Proc ICSLP
  16. ai, 2007, knowledge consistent user simulations for dialog systems, Proc ICSLP
  17. 10.1109/ASRU.2005.1566485 · DOI · Paper page
  18. bunt, 1981, Rules for the interpretation evaluation and generation of dialogue acts, 99
  19. core, 1997, coding dialogs with the damsl annotation scheme, Working Notes of the AAAI Fall Symp Communicative Action in Humans and Machines
  20. henderson, 2005, hybrid reinforcement/supervised learning for dialogue policies from communicator data, Proc Workshop Knowl Reasoning Practical Dialog Syst IJCAI
  21. 10.1109/89.817450 · DOI · Paper page
  22. 10.1109/ASRU.2005.1566498 · DOI
  23. 10.1109/ASRU.2007.4430167 · DOI
  24. young, 2005, The hidden information state approach to dialogue management
  25. sutton, 1998, Reinforcement Learning
  26. 10.1109/89.817450 · DOI · Paper page
  27. young, 2002, talking to machines (statistically speaking), Proc ICSLP, 9
  28. scheffler, 2002, Automatic Design of Spoken Dialogue Systems
  29. traum, 1999, Foundations of Rational Agency, 169, 10.1007/978-94-015-9204-8_8 · DOI
  30. 10.3115/1072133.1072148 · DOI · Paper page
  31. young, 2007, CUED standard dialogue acts
  32. 10.1162/089120100561737 · DOI · Paper page
  33. bohus, 2003, ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda, Proc EUROSPEECH, 10.21437/Eurospeech.2003-255 · DOI · Paper page
  34. wei, 1999, an agenda-based dialog management architecture for spoken language systems, Proc ASRU
  35. 10.3115/1556328.1556330 · DOI
  36. schatzmann, 2007, statistical user simulation with a hidden agenda, Proc SIGDial

Cited by

See all 94

Metadata

Authors
Schatzmann, J., & Young, S.
Venue
IEEE Transactions on Audio, Speech, and Language Processing
Published
2009-05
Volume
17
Issue
4
Pages
733-747
ISSN
1558-7916 (ISSN-L)
OpenAlex
W2120045257
Cited by
94
References
3
FWCI
1.81
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: The Hidden Agenda User Simulation Model. https://app.cochat.ai/papers/10.1109/tasl.2008.2012071
The paper
Schatzmann, J., & Young, S. (2009). The Hidden Agenda User Simulation Model. IEEE Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/tasl.2008.2012071

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.