Learning mixed initiative dialog strategies by using reinforcement learning on both conversants

Michael S. English; Peter A. Heeman

doi:10.3115/1220575.1220702

Learning mixed initiative dialog strategies by using reinforcement learning on both conversants

Michael S. English, Peter A. Heeman

Institute on Development and Disability

Research output: Contribution to conference › Paper › peer-review

28 Scopus citations

Abstract

This paper describes an application of reinforcement learning to determine a dialog policy for a complex collaborative task where policies for both the system and a proxy for a user of the system are learned simultaneously. With this approach a useful dialog policy is learned without the drawbacks of other approaches that require significant human interaction. The specific task that the agents were trained on was chosen for its complexity and requirement that both conversants bring task knowledge to the interaction, thus ensuring its collaborative nature. The results of our experiment show that you can use reinforcement learning to create an effective dialog policy, which employs a mixed initiative strategy, without the drawbacks of large amounts of data or significant human input.

Original language	English (US)
Pages	1011-1018
Number of pages	8
DOIs	https://doi.org/10.3115/1220575.1220702
State	Published - 2005
Event	Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT - Vancouver, BC, Canada Duration: Oct 6 2005 → Oct 8 2005

Other

Other	Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT
Country/Territory	Canada
City	Vancouver, BC
Period	10/6/05 → 10/8/05

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Information Systems

Access to Document

10.3115/1220575.1220702

Cite this

English, M. S., & Heeman, P. A. (2005). Learning mixed initiative dialog strategies by using reinforcement learning on both conversants. 1011-1018. Paper presented at Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada. https://doi.org/10.3115/1220575.1220702

Learning mixed initiative dialog strategies by using reinforcement learning on both conversants. / English, Michael S.; Heeman, Peter A.
2005. 1011-1018 Paper presented at Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada.

Research output: Contribution to conference › Paper › peer-review

English, MS & Heeman, PA 2005, 'Learning mixed initiative dialog strategies by using reinforcement learning on both conversants', Paper presented at Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada, 10/6/05 - 10/8/05 pp. 1011-1018. https://doi.org/10.3115/1220575.1220702

English MS, Heeman PA. Learning mixed initiative dialog strategies by using reinforcement learning on both conversants. 2005. Paper presented at Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada. doi: 10.3115/1220575.1220702

English, Michael S. ; Heeman, Peter A. / Learning mixed initiative dialog strategies by using reinforcement learning on both conversants. Paper presented at Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada.8 p.

@conference{6ee51e6dde6d43dca8d068c80cb350a0,

title = "Learning mixed initiative dialog strategies by using reinforcement learning on both conversants",

abstract = "This paper describes an application of reinforcement learning to determine a dialog policy for a complex collaborative task where policies for both the system and a proxy for a user of the system are learned simultaneously. With this approach a useful dialog policy is learned without the drawbacks of other approaches that require significant human interaction. The specific task that the agents were trained on was chosen for its complexity and requirement that both conversants bring task knowledge to the interaction, thus ensuring its collaborative nature. The results of our experiment show that you can use reinforcement learning to create an effective dialog policy, which employs a mixed initiative strategy, without the drawbacks of large amounts of data or significant human input.",

author = "English, {Michael S.} and Heeman, {Peter A.}",

year = "2005",

doi = "10.3115/1220575.1220702",

language = "English (US)",

pages = "1011--1018",

note = "Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT ; Conference date: 06-10-2005 Through 08-10-2005",

}

TY - CONF

T1 - Learning mixed initiative dialog strategies by using reinforcement learning on both conversants

AU - English, Michael S.

AU - Heeman, Peter A.

PY - 2005

Y1 - 2005

N2 - This paper describes an application of reinforcement learning to determine a dialog policy for a complex collaborative task where policies for both the system and a proxy for a user of the system are learned simultaneously. With this approach a useful dialog policy is learned without the drawbacks of other approaches that require significant human interaction. The specific task that the agents were trained on was chosen for its complexity and requirement that both conversants bring task knowledge to the interaction, thus ensuring its collaborative nature. The results of our experiment show that you can use reinforcement learning to create an effective dialog policy, which employs a mixed initiative strategy, without the drawbacks of large amounts of data or significant human input.

AB - This paper describes an application of reinforcement learning to determine a dialog policy for a complex collaborative task where policies for both the system and a proxy for a user of the system are learned simultaneously. With this approach a useful dialog policy is learned without the drawbacks of other approaches that require significant human interaction. The specific task that the agents were trained on was chosen for its complexity and requirement that both conversants bring task knowledge to the interaction, thus ensuring its collaborative nature. The results of our experiment show that you can use reinforcement learning to create an effective dialog policy, which employs a mixed initiative strategy, without the drawbacks of large amounts of data or significant human input.

UR - http://www.scopus.com/inward/record.url?scp=70349132784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349132784&partnerID=8YFLogxK

U2 - 10.3115/1220575.1220702

DO - 10.3115/1220575.1220702

M3 - Paper

AN - SCOPUS:70349132784

SP - 1011

EP - 1018

T2 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT

Y2 - 6 October 2005 through 8 October 2005

ER -

Learning mixed initiative dialog strategies by using reinforcement learning on both conversants

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this