Robust parsing of severely corrupted spoken utterances

  • Authors:
  • Egidio P. Giachin;Claudio Rullent

  • Affiliations:
  • CSELT - Centro Studi e Laboratori Telecomunicazioni, Torino, Italy;CSELT - Centro Studi e Laboratori Telecomunicazioni, Torino, Italy

  • Venue:
  • COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1
  • Year:
  • 1988

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes a technique for enabling a speech understanding system to deal with sentences for which some monosyllabic words are not recognized. Such words are supposed to act as mere syntactic markers within the system linguistic domain. This result is achieved by combining a modified caseframe approach to linguistic knowledge representation with a parsing strategy able to integrate expectations from the language model and predictions from words. Experimental results show that the proposed technique permits to greatly increase the quota of corrupted sentences correctly understandable without sensibly decreasing parsing efficiency.