Metareasoning for More Effective Human-Computer Dialogue

Abstract

The research project explores specific meta-dialogue behaviors in terms of both how a system could be made to perform them, and to what extent they can increase overall system performance. We focus on two types of meta-dialogue capabilities: ability to detect and recover from anomalous dialogue patterns in simple exchanges, and on-line extensions or changes to working vocabulary. Our main method involves detailed representation of the dialogue context, separating domain, language, and dialogue specific aspects, and significant amounts of meta-reasoning about the system's processing of these representations. An existing logical inference system, ALMA/CARNE, developed as part of a pilot study, is being used in an implementation phase of this work. We are also engaged in a study of existing dialogue corpora to investigate the range and frequency of meta-dialogue expressions in different task domains.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 31, 2002
Accession Number
ADA414209

Entities

People

  • Don Perlis
  • Mike Anderson

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Cognitive Science
  • Computations
  • Computers
  • Dialogue Systems
  • Frequency
  • Intelligent Systems
  • Language
  • Maryland
  • Natural Languages
  • New Mexico
  • Pilot Studies
  • Reasoning
  • Universities
  • Vocabulary
  • Words (Language)

Readers

  • Artificial Intelligence
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks