A relaxation method for understanding spontaneous speech utterances

  • Authors:
  • Stephanie Seneff

  • Affiliations:
  • Massachusetts Institute of Technology, Cambridge, Massachusetts

  • Venue:
  • HLT '91 Proceedings of the workshop on Speech and Natural Language
  • Year:
  • 1992

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes an extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a full linguistic analysis fails. This "robust" parsing capability was achieved through minor extensions of pre-existing components already in place for the full linguistic analysis component. Robust parsing is applied only after a full analysis has failed, and it involves the two stages of 1) parsing a set of phrases and clauses, and 2) gluing them together to obtain a single semantic frame encoding the full meaning of the sentence. We have assessed the degree of success of the robust parsing mechanism through a breakdown of the performance of robustly parsed vs. fully parsed sentences on the October '91 "dry-run" test set. It was clear that the robust parser allowed us to answer many more questions correctly, as over a third of the sentences were not covered by the grammar. We also report here on the performance of the system on the February '92 test sentences, and discuss some issues with regard to the evaluation methodology.