A generic architecture and dialogue model for multimodal interaction

D.H.W. Hofs; Hendrikus J.A. op den Akker; Antinus Nijholt

A generic architecture and dialogue model for multimodal interaction

D.H.W. Hofs, Hendrikus J.A. op den Akker, Antinus Nijholt

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

78 Downloads (Pure)

Abstract

This paper presents a generic architecture and a dialogue model for multimodal interaction. Architecture and model are transparent and have been used for different task domains. In this paper the emphasis is on their use for the navigation task in a virtual environment. The dialogue model is based on the information state approach and the recognition of dialogue acts. We explain how pairs of backward and forward looking tags and the preference rules of the dialogue act determiner together determine the structure of the dialogues that can be handled by the system. The system action selection mechanism and the problem of reference resolution are discussed in detail.

Original language	Undefined
Title of host publication	Proceedings of the 1st Nordic Symposium on Multimodal Communication
Editors	P. Paggio, K. Jokinen, A. Jönsson
Place of Publication	Copenhagen
Publisher	CST Publication, Center for Sprokteknologi
Pages	79-91
Number of pages	13
Publication status	Published - Sep 2003
Event	1st Nordic Symposium on Multimodal Communication 2003 - Copenhagen, Denmark Duration: 25 Sep 2003 → 26 Sep 2003

Publication series

Name
Publisher	CST Publication, Center for Sprogteknologi
Volume	1
ISSN (Print)	1600-339X

Workshop

Workshop	1st Nordic Symposium on Multimodal Communication 2003
Country/Territory	Denmark
City	Copenhagen
Period	25/09/03 → 26/09/03

Keywords

IR-66310
METIS-217378
EWI-6698

Access to Document

Cite this

@inproceedings{b8f0a4dd96f244ffa9ea316abe279c81,

title = "A generic architecture and dialogue model for multimodal interaction",

abstract = "This paper presents a generic architecture and a dialogue model for multimodal interaction. Architecture and model are transparent and have been used for different task domains. In this paper the emphasis is on their use for the navigation task in a virtual environment. The dialogue model is based on the information state approach and the recognition of dialogue acts. We explain how pairs of backward and forward looking tags and the preference rules of the dialogue act determiner together determine the structure of the dialogues that can be handled by the system. The system action selection mechanism and the problem of reference resolution are discussed in detail.",

keywords = "IR-66310, METIS-217378, EWI-6698",

author = "D.H.W. Hofs and {op den Akker}, {Hendrikus J.A.} and Antinus Nijholt",

note = "Imported from HMI; null ; Conference date: 25-09-2003 Through 26-09-2003",

year = "2003",

month = sep,

language = "Undefined",

publisher = "CST Publication, Center for Sprokteknologi",

pages = "79--91",

editor = "P. Paggio and K. Jokinen and A. J{\"o}nsson",

booktitle = "Proceedings of the 1st Nordic Symposium on Multimodal Communication",

}

Hofs, DHW, op den Akker, HJA & Nijholt, A 2003, A generic architecture and dialogue model for multimodal interaction. in P Paggio, K Jokinen & A Jönsson (eds), Proceedings of the 1st Nordic Symposium on Multimodal Communication. CST Publication, Center for Sprokteknologi, Copenhagen, pp. 79-91, 1st Nordic Symposium on Multimodal Communication 2003, Copenhagen, Denmark, 25/09/03.

A generic architecture and dialogue model for multimodal interaction. / Hofs, D.H.W.; op den Akker, Hendrikus J.A.; Nijholt, Antinus.

Proceedings of the 1st Nordic Symposium on Multimodal Communication. ed. / P. Paggio; K. Jokinen; A. Jönsson. Copenhagen : CST Publication, Center for Sprokteknologi, 2003. p. 79-91.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A generic architecture and dialogue model for multimodal interaction

AU - Hofs, D.H.W.

AU - op den Akker, Hendrikus J.A.

AU - Nijholt, Antinus

N1 - Imported from HMI

PY - 2003/9

Y1 - 2003/9

N2 - This paper presents a generic architecture and a dialogue model for multimodal interaction. Architecture and model are transparent and have been used for different task domains. In this paper the emphasis is on their use for the navigation task in a virtual environment. The dialogue model is based on the information state approach and the recognition of dialogue acts. We explain how pairs of backward and forward looking tags and the preference rules of the dialogue act determiner together determine the structure of the dialogues that can be handled by the system. The system action selection mechanism and the problem of reference resolution are discussed in detail.

AB - This paper presents a generic architecture and a dialogue model for multimodal interaction. Architecture and model are transparent and have been used for different task domains. In this paper the emphasis is on their use for the navigation task in a virtual environment. The dialogue model is based on the information state approach and the recognition of dialogue acts. We explain how pairs of backward and forward looking tags and the preference rules of the dialogue act determiner together determine the structure of the dialogues that can be handled by the system. The system action selection mechanism and the problem of reference resolution are discussed in detail.

KW - IR-66310

KW - METIS-217378

KW - EWI-6698

M3 - Conference contribution

SP - 79

EP - 91

BT - Proceedings of the 1st Nordic Symposium on Multimodal Communication

A2 - Paggio, P.

A2 - Jokinen, K.

A2 - Jönsson, A.

PB - CST Publication, Center for Sprokteknologi

CY - Copenhagen

Y2 - 25 September 2003 through 26 September 2003

ER -