Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
We propose a method for learning dialogue management policies from a fixed data set. The method addresses the challenges posed by Information State Update (ISU)-based dialogue systems, which represent the state of a dialogue as a large set of features, resulting in a very large state space and a huge policy space. To address the problem that any fixed data set will only provide information about small portions of these state and policy spaces, we propose a hybrid model that combines reinforcement learning with supervised learning. The reinforcement learning is used to optimize a measure of dialogue reward, while the supervised learning is used to restrict the learned policy to the portions of these spaces for which we have data. We also use linear function approximation to address the need to generalize from a fixed amount of data to large state spaces. To demonstrate the effectiveness of this method on this challenging task, we trained this model on the COMMUNICATOR corpus, to which we have added annotations for user actions and Information States. When tested with a user simulation trained on a different part of the same data set, our hybrid model outperforms a pure supervised learning model and a pure reinforcement learning model. It also outperforms the hand-crafted systems on the COMMUNICATOR data, according to automatic evaluation measures, improving over the average COMMUNICATOR system policy by 10%. The proposed method will improve techniques for bootstrapping and automatic optimization of dialogue management policies from limited initial data sets.
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
Cites
SCHATZMANN, J., WEILHAMMER, K., STUTTLE, M., & YOUNG, S. (2006) · The Knowledge Engineering Review · doi:10.1017/s0269888906000944 · Cited by 336 · cited 2×
“…amount of dialogue system work that has relied on simulated users (e.g., Scheffler and Young 2002; Pietquin 2004; Georgila, Henderson, and Lemon 2006; Schatzmann et al. 2006), to date there has not been a systematic experiment that validates this methodology against results from human users.”
Background
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
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Levine, S., Kumar, A., Tucker, G., & Fu, J. (2020) · arXiv · doi:10.48550/arxiv.2005.01643 · Cited by 824
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
Fu, J., Kumar, A., Nachum, O., Tucker, G., & Levine, S. (2020) · arXiv · doi:10.48550/arxiv.2004.07219 · Cited by 310
Recent advances in deep learning based dialogue systems: a systematic survey
Ni, J., Young, T., Pandelea, V., Xue, F., & Cambria, E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10248-8 · Cited by 264
Improving recommender systems with adaptive conversational strategies
Mahmood, T., & Ricci, F. (2009) · Proceedings of the 20th ACM conference on Hypertext and hypermedia · doi:10.1145/1557914.1557930 · Cited by 259
Metadata
- Authors
- Henderson, J., Lemon, O., & Georgila, K.
- Venue
- Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2008-12
- Volume
- 34
- Issue
- 4
- Pages
- 487-511
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W2021151961
- Cited by
- 121
- References
- 1
- FWCI
- 16.96
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets. https://app.cochat.ai/papers/10.1162/coli.2008.07-028-r2-05-82
- The paper
- Henderson, J., Lemon, O., & Georgila, K. (2008). Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets. Computational Linguistics. https://doi.org/10.1162/coli.2008.07-028-r2-05-82
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.