Learning user simulations for information state update dialogue systems
The DOI matches its Crossref record.
Abstract
This paper describes and compares two methods for simulating user behaviour in spoken dialogue systems. User simulations are important for automatic dialogue strategy learning and the evaluation of competing strategies. Our methods are designed for use with "Information State Update" (ISU)-based dialogue systems. The first method is based on supervised learning using linear feature combination and a normalised exponential output function. The user is modelled as a stochastic process which selects user actions ( pairs) based on features of the current dialogue state, which encodes the whole history of the dialogue. The second method uses n-grams of speech act, task pairs, restricting the length of the history considered by the order of the n-gram. Both models were trained and evaluated on a subset of the COMMUNICATOR corpus, to which we added annotations for user actions and Information States. The model based on linear feature combination has a perplexity of 2.08 whereas the best n-gram (4-gram) has a perplexity of 3.58. Each one of the user models ran against a system policy trained on the same corpus with a method similar to the one used for our linear feature combination model. The quality of the simulated dialogues produced was then measured as a function of the filled slots, confirmed slots, and number of actions performed by the system in each dialogue. In this experiment both the linear feature combination model and the best n-grams (5-gram and 4-gram) produced similar quality simulated dialogues.
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.
Integrity signals
Registry
Cites
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.
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
Cited by
POMDP-Based Statistical Spoken Dialog Systems: A Review
Young, S., Gasic, M., Thomson, B., & Williams, J. D. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2225812 · Cited by 882
SCHATZMANN, J., WEILHAMMER, K., STUTTLE, M., & YOUNG, S. (2006) · The Knowledge Engineering Review · doi:10.1017/s0269888906000944 · Cited by 336
“As such, the user model must be able to predict user responses that a real user might give in the same dialogue context and it must also represent the statistical distribution over all types of user behaviour and user response.”
InfluentialMachine learning for spoken dialogue systems
Lemon, O., & Pietquin, O. (2007) · Interspeech 2007 · doi:10.21437/interspeech.2007-705 · Cited by 104
Self-citationBeing Old Doesn’t Mean Acting Old: How Older Users Interact with Spoken Dialog Systems
Wolters, M., Georgila, K., Moore, J. D., & MacPherson, S. E. (2009) · ACM Transactions on Accessible Computing · doi:10.1145/1525840.1525842 · Cited by 60
Self-citationUser Modeling for Task Oriented Dialogues
Gur, I., Hakkani-Tur, D., Tur, G., & Shah, P. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639652 · Cited by 48
Metadata
- Authors
- Georgila, K., Henderson, J., & Lemon, O.
- Venue
- Interspeech 2005
- Publisher
- ISCA
- Published
- 2005-09-04
- Pages
- 893-896
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W160067033
- Cited by
- 127
- References
- 0
- FWCI
- 7.87
- Type
- conference paper
- 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: Learning user simulations for information state update dialogue systems. https://app.cochat.ai/papers/10.21437/interspeech.2005-401
- The paper
- Georgila, K., Henderson, J., & Lemon, O. (2005). Learning user simulations for information state update dialogue systems. Interspeech 2005. https://doi.org/10.21437/interspeech.2005-401
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.