Incremental Parsing with Reference Interaction

Abstract

We present a general architecture for incremental interaction between modules in a speech-to-intention continuous understanding dialogue system. This architecture is then instantiated in the form of an incremental parser which receives suitability feedback on NP constituents from a reference resolution module. Oracle results indicate that perfect NP suitability judgments can provide a labelled-bracket error reduction of as much as 42% and an efficiency improvement of 30%. Preliminary experiments in which the parser incorporates feedback judgments based on the set of referents found in the discourse context achieve a maximum error reduction of 9.3% and efficiency gain of 4.6%. The parser is also able to incrementally instantiate the semantics of underspecified pronouns based on matches from the discourse context. These results suggest that the architecture holds promise as a platform for incremental parsing supporting continuous understanding.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2004
Accession Number
ADA454819

Entities

People

  • James F. Allen
  • Joel Tetreault
  • Scott C. Stoness

Organizations

  • University of Rochester

Tags

Communities of Interest

  • Advanced Electronics
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accuracy
  • Artificial Intelligence
  • Automated Speech Recognition
  • Classification
  • Computational Linguistics
  • Computational Science
  • Computer Science
  • Dialogue Systems
  • Errors
  • Grammars
  • Language
  • Natural Language Processing
  • Natural Languages
  • Probability
  • Probability Distributions
  • Recognition
  • Standards

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Database Systems and Applications
  • Enterprise Information Systems Architecture and Joint Command Capability Interoperability Support.