Clarification dialogues as measure to increase robustness in a spoken dialogue system

Authors:
Elisabeth Maier;Norbert Reithinger;Jan Alexandersson
Affiliations:
DFKI GmbH, Saarbrücken, Germany;DFKI GmbH, Saarbrücken, Germany;DFKI GmbH, Saarbrücken, Germany
Venue:
ISDS '97 Interactive Spoken Dialog Systems on Bringing Speech and NLP Together in Real Applications
Year:
1997

Citing 4
Cited 1

Using an Interpretation System - Some Observations in Hidden Operator Simulations of 'VERBMOBIL'

ECAI '96 Workshop on Dialogue Processing in Spoken Language Systems
Minimizing Cumulative Error in Discourse Context

ECAI '96 Workshop on Dialogue Processing in Spoken Language Systems
Insights into the dialogue processing of VERBMOBIL

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
A robust system for natural spoken dialogue

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics

Turn off the radio and call again: how acoustic clues can improve dialogue management

ISDS '97 Interactive Spoken Dialog Systems on Bringing Speech and NLP Together in Real Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

A number of methods are implemented in the face-to-face translation system Verbmobil to improve its robustness. In this paper, we describe clarification dialogues as one method to deal with incomplete or inconsistent information. Currently, three types of clarification dialogues are realized: subdialogues concerning phonological ambiguities, unknown words and semantic inconsistencies. For each clarification type we discuss the detection of situations and system states which lead to their initialization and explain the information flow during processing.