EVALUATING EFFECTIVENESS AND PORTABILITY OF REINFORCEMENT LEARNED DIALOGUE STRATEGIES WITH REAL USERS: THE TALK TOWNINFO EVALUATION
The DOI matches its Crossref record.
Abstract
We report evaluation results for real users of a learnt dialogue management policy versus a hand-coded policy in the TALK project's "Townlnfo" tourist information system. The learnt policy, for filling and confirming information slots, was derived from COMMUNICATOR (flight-booking) data using reinforcement learning (RL) as described in [2], ported to the tourist information domain (using a general method that we propose here), and tested using 18 human users in 180 dialogues, who also used a state-of-the-art hand- coded dialogue policy embedded in an otherwise identical system. We found that users of the (ported) learned policy had an average gain in perceived task completion of 14.2% (from 67.6% to 81.8% at p < .03), that the hand-coded policy dialogues had on average 3.3 more system turns (p < .01), and that the user satisfaction results were comparable, even though the policy was learned for a different domain. Combining these in a dialogue reward score, we found a 14.4% increase for the learnt policy (a 23.8% relative increase, p < .03). These results are important because they show a) that results for real users are consistent with results for automatic evaluation [2] of learned policies using simulated users [3, 4], b) that a policy learned using linear function approximation over a very large policy space [2] is effective for real users, and c) that policies learned using data for one domain can be used successfully in other domains. We also present a qualitative discussion of the learnt policy.
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
Agenda-based user simulation for bootstrapping a POMDP dialogue system
Schatzmann, J., Thomson, B., Weilhammer, K., Ye, H., & Young, S. (2007) · Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX - NAACL '07 · doi:10.3115/1614108.1614146 · Cited by 332
Machine learning for spoken dialogue systems
Lemon, O., & Pietquin, O. (2007) · Interspeech 2007 · doi:10.21437/interspeech.2007-705 · Cited by 104
Self-citationEnhancement of Conversational Agents By Means of Multimodal Interaction
López-Cózar, R., Callejas, Z., Espejo, G., & Griol, D. (2011) · Conversational Agents and Natural Language Interaction · doi:10.4018/978-1-60960-617-6.ch010 · Cited by 18
“For example, Lemon et al. (2006a) used frames to combine multimodal information in a conversational agent that provided information about hotels, restaurants and bars in a town.”
MethodUsing dialogue acts to learn better repair strategies for spoken dialogue systems
Frampton, M., & Lemon, O. (2008) · 2008 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2008.4518792 · Cited by 9
Self-citation
Metadata
- Authors
- Lemon, O., Georgila, K., & Henderson, J.
- Venue
- 2006 IEEE Spoken Language Technology Workshop
- Publisher
- IEEE
- Published
- 2006
- Pages
- 178-181
- OpenAlex
- W2101445408
- Cited by
- 73
- References
- 0
- FWCI
- 9.12
- 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: EVALUATING EFFECTIVENESS AND PORTABILITY OF REINFORCEMENT LEARNED DIALOGUE STRATEGIES WITH REAL USERS: THE TALK TOWNINFO EVALUATION. https://app.cochat.ai/papers/10.1109/slt.2006.326774
- The paper
- Lemon, O., Georgila, K., & Henderson, J. (2006). EVALUATING EFFECTIVENESS AND PORTABILITY OF REINFORCEMENT LEARNED DIALOGUE STRATEGIES WITH REAL USERS: THE TALK TOWNINFO EVALUATION. 2006 IEEE Spoken Language Technology Workshop. https://doi.org/10.1109/slt.2006.326774
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.