Exploring initiative strategies using computer simulation

Fan Yang, Peter Heeman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We envision that next-generation spoken dialogue systems will be mixed-initiative. However, it is unclear how exactly a mixed-initiative strategy should be designed; under what circumstances should the system take the initiative, and under what circumstances should it let the user do so. The initiative strategies used in human-human conversation are a good starting point, because they are natural for the user to follow. Studying human-human conversation, however, only gives a descriptive account of human strategies. In this paper, we explore the use of computer simulation to better understand human conventions and give an explanatory account. We have two software agents solve a collaborative task using different initiative strategies, the first derived from analysis of human-human dialogues, and two alternatives based on proposals in the literature. Our simulation results show that the former is more efficient than the others. This helps support the explanation that people use an initiative strategy that minimizes collaborative effort.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Pages1069-1072
Number of pages4
Volume2
StatePublished - 2007
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: Aug 27 2007Aug 31 2007

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CountryBelgium
CityAntwerp
Period8/27/078/31/07

Fingerprint

Software agents
computer simulation
Computer Simulation
Computer simulation
conversation
communication technology
Spoken Dialogue Systems
Mixed Strategy
dialogue
Software Agents
Strategy
Human
simulation
Minimise
Alternatives

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modeling and Simulation
  • Linguistics and Language
  • Communication

Cite this

Yang, F., & Heeman, P. (2007). Exploring initiative strategies using computer simulation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2, pp. 1069-1072)

Exploring initiative strategies using computer simulation. / Yang, Fan; Heeman, Peter.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2 2007. p. 1069-1072.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yang, F & Heeman, P 2007, Exploring initiative strategies using computer simulation. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2, pp. 1069-1072, 8th Annual Conference of the International Speech Communication Association, Interspeech 2007, Antwerp, Belgium, 8/27/07.
Yang F, Heeman P. Exploring initiative strategies using computer simulation. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2. 2007. p. 1069-1072
Yang, Fan ; Heeman, Peter. / Exploring initiative strategies using computer simulation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2 2007. pp. 1069-1072
@inproceedings{850bec3fdf294607a421c6adc9a8e7a3,
title = "Exploring initiative strategies using computer simulation",
abstract = "We envision that next-generation spoken dialogue systems will be mixed-initiative. However, it is unclear how exactly a mixed-initiative strategy should be designed; under what circumstances should the system take the initiative, and under what circumstances should it let the user do so. The initiative strategies used in human-human conversation are a good starting point, because they are natural for the user to follow. Studying human-human conversation, however, only gives a descriptive account of human strategies. In this paper, we explore the use of computer simulation to better understand human conventions and give an explanatory account. We have two software agents solve a collaborative task using different initiative strategies, the first derived from analysis of human-human dialogues, and two alternatives based on proposals in the literature. Our simulation results show that the former is more efficient than the others. This helps support the explanation that people use an initiative strategy that minimizes collaborative effort.",
author = "Fan Yang and Peter Heeman",
year = "2007",
language = "English (US)",
isbn = "9781605603162",
volume = "2",
pages = "1069--1072",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

}

TY - GEN

T1 - Exploring initiative strategies using computer simulation

AU - Yang, Fan

AU - Heeman, Peter

PY - 2007

Y1 - 2007

N2 - We envision that next-generation spoken dialogue systems will be mixed-initiative. However, it is unclear how exactly a mixed-initiative strategy should be designed; under what circumstances should the system take the initiative, and under what circumstances should it let the user do so. The initiative strategies used in human-human conversation are a good starting point, because they are natural for the user to follow. Studying human-human conversation, however, only gives a descriptive account of human strategies. In this paper, we explore the use of computer simulation to better understand human conventions and give an explanatory account. We have two software agents solve a collaborative task using different initiative strategies, the first derived from analysis of human-human dialogues, and two alternatives based on proposals in the literature. Our simulation results show that the former is more efficient than the others. This helps support the explanation that people use an initiative strategy that minimizes collaborative effort.

AB - We envision that next-generation spoken dialogue systems will be mixed-initiative. However, it is unclear how exactly a mixed-initiative strategy should be designed; under what circumstances should the system take the initiative, and under what circumstances should it let the user do so. The initiative strategies used in human-human conversation are a good starting point, because they are natural for the user to follow. Studying human-human conversation, however, only gives a descriptive account of human strategies. In this paper, we explore the use of computer simulation to better understand human conventions and give an explanatory account. We have two software agents solve a collaborative task using different initiative strategies, the first derived from analysis of human-human dialogues, and two alternatives based on proposals in the literature. Our simulation results show that the former is more efficient than the others. This helps support the explanation that people use an initiative strategy that minimizes collaborative effort.

UR - http://www.scopus.com/inward/record.url?scp=56149118245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149118245&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781605603162

VL - 2

SP - 1069

EP - 1072

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ER -