a model for incremental grounding in spoken dialogue systems

Thomas Visser, David Traum, David DeVault, Hendrikus J.A. op den Akker

Abstract

Recent advances in incremental language processing for dialogue systems promise to enable more natural conversation between humans and computers. By analyzing the user's utterance while it is still in progress, systems can provide more human-like overlapping and backchannel responses to convey their level of understanding and respond more quickly. In this paper, we look at examples of several overlapping response types in human-human dialogues, and present an initial computational model of the incremental grounding process in these responses. Additionally, we describe an implementation of this model in a virtual human dialogue system that can provide backchannels, head nods, frowns, completions and low latency responses.
Original languageUndefined
Title of host publicationJoint Proceedings of the 2012 IVA Workshops
Place of PublicationMagdeburg, Germany
PublisherOtto von Guericke University Magdeburg
Pages101-108
Number of pages8
ISBN (Print)978-3-940961-83-9
StatePublished - 15 Sep 2012

Publication series

Name
PublisherOtto von Guericke University Magdeburg

Fingerprint

Backchannel
Dialogue systems
Completion
Latency
Grounding
Computational model
Language processing

Keywords

  • EWI-24287
  • HMI-HF: Human Factors
  • Spoken dialogue systems
  • METIS-302630
  • grounding
  • IR-89579
  • incremental language processing

Cite this

Visser, T., Traum, D., DeVault, D., & op den Akker, H. J. A. (2012). a model for incremental grounding in spoken dialogue systems. In Joint Proceedings of the 2012 IVA Workshops (pp. 101-108). Magdeburg, Germany: Otto von Guericke University Magdeburg.

Visser, Thomas; Traum, David; DeVault, David; op den Akker, Hendrikus J.A. / a model for incremental grounding in spoken dialogue systems.

Joint Proceedings of the 2012 IVA Workshops. Magdeburg, Germany : Otto von Guericke University Magdeburg, 2012. p. 101-108.

Research output: Scientific - peer-reviewConference contribution

@inbook{533e7ca11c6b4f17818d546899c5b662,
title = "a model for incremental grounding in spoken dialogue systems",
abstract = "Recent advances in incremental language processing for dialogue systems promise to enable more natural conversation between humans and computers. By analyzing the user's utterance while it is still in progress, systems can provide more human-like overlapping and backchannel responses to convey their level of understanding and respond more quickly. In this paper, we look at examples of several overlapping response types in human-human dialogues, and present an initial computational model of the incremental grounding process in these responses. Additionally, we describe an implementation of this model in a virtual human dialogue system that can provide backchannels, head nods, frowns, completions and low latency responses.",
keywords = "EWI-24287, HMI-HF: Human Factors, Spoken dialogue systems, METIS-302630, grounding, IR-89579, incremental language processing",
author = "Thomas Visser and David Traum and David DeVault and {op den Akker}, {Hendrikus J.A.}",
year = "2012",
month = "9",
isbn = "978-3-940961-83-9",
publisher = "Otto von Guericke University Magdeburg",
pages = "101--108",
booktitle = "Joint Proceedings of the 2012 IVA Workshops",

}

Visser, T, Traum, D, DeVault, D & op den Akker, HJA 2012, a model for incremental grounding in spoken dialogue systems. in Joint Proceedings of the 2012 IVA Workshops. Otto von Guericke University Magdeburg, Magdeburg, Germany, pp. 101-108.

a model for incremental grounding in spoken dialogue systems. / Visser, Thomas; Traum, David; DeVault, David; op den Akker, Hendrikus J.A.

Joint Proceedings of the 2012 IVA Workshops. Magdeburg, Germany : Otto von Guericke University Magdeburg, 2012. p. 101-108.

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - a model for incremental grounding in spoken dialogue systems

AU - Visser,Thomas

AU - Traum,David

AU - DeVault,David

AU - op den Akker,Hendrikus J.A.

PY - 2012/9/15

Y1 - 2012/9/15

N2 - Recent advances in incremental language processing for dialogue systems promise to enable more natural conversation between humans and computers. By analyzing the user's utterance while it is still in progress, systems can provide more human-like overlapping and backchannel responses to convey their level of understanding and respond more quickly. In this paper, we look at examples of several overlapping response types in human-human dialogues, and present an initial computational model of the incremental grounding process in these responses. Additionally, we describe an implementation of this model in a virtual human dialogue system that can provide backchannels, head nods, frowns, completions and low latency responses.

AB - Recent advances in incremental language processing for dialogue systems promise to enable more natural conversation between humans and computers. By analyzing the user's utterance while it is still in progress, systems can provide more human-like overlapping and backchannel responses to convey their level of understanding and respond more quickly. In this paper, we look at examples of several overlapping response types in human-human dialogues, and present an initial computational model of the incremental grounding process in these responses. Additionally, we describe an implementation of this model in a virtual human dialogue system that can provide backchannels, head nods, frowns, completions and low latency responses.

KW - EWI-24287

KW - HMI-HF: Human Factors

KW - Spoken dialogue systems

KW - METIS-302630

KW - grounding

KW - IR-89579

KW - incremental language processing

M3 - Conference contribution

SN - 978-3-940961-83-9

SP - 101

EP - 108

BT - Joint Proceedings of the 2012 IVA Workshops

PB - Otto von Guericke University Magdeburg

ER -

Visser T, Traum D, DeVault D, op den Akker HJA. a model for incremental grounding in spoken dialogue systems. In Joint Proceedings of the 2012 IVA Workshops. Magdeburg, Germany: Otto von Guericke University Magdeburg. 2012. p. 101-108.