Hostname: page-component-78c5997874-94fs2 Total loading time: 0 Render date: 2024-11-15T01:39:30.151Z Has data issue: false hasContentIssue false
  • English
  • Français

Surface-marker-based dialog modelling: A progress report on the MAREDI project

Published online by Cambridge University Press:  25 November 2003

SYLVAIN DELISLE ,
BERNARD MOULIN  and
TERRY COPECK
SYLVAIN DELISLE
Affiliation:
Département de mathématiques et d'informatique, Université du Québec à Trois Rivières, C.P. 500, Trois-Rivières, Québec, Canada G9A 5H7 e-mail: Sylvain_Delisle@uqtr.ca
BERNARD MOULIN
Affiliation:
Département d'informatique, Université Laval, Pavillon Pouliot, Sainte-Foy, Quèbec, Canada G1K 7P4 e-mail: moulin@ift.ulaval.ca
TERRY COPECK
Affiliation:
School of Information Technology and Engineering, University of Ottawa, Ottawa, Ontario, Canada K1N 6N5 e-mail: terry@site.uottawa.ca
Get access Rights & Permissions [Opens in a new window]

Abstract

Most information systems that deal with natural language texts do not tolerate much deviation from their idealized and simplified model of language. Spoken dialog is notoriously ungrammatical, however. Because the MAREDI project focuses in particular on the automatic analysis of scripted dialogs, we needed to develop a robust capacity to analyze transcribed spoken language. This paper summarizes the current state of our work. It presents the main elements of our approach, which is based on exploiting surface markers as the best route to the semantics of the conversation modelled. We highlight the foundations of our particular conversational model, and give an overview of the MAREDI system. We then discuss its three key modules, a connectionist network to recognise speech acts, a robust syntactic analyzer, and a semantic analyzer.

Type
Papers
Information
Natural Language Engineering , Volume 9 , Issue 4 , December 2003 , pp. 325 - 363
Copyright
© 2003 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)