Do CFG-based language models need agreement constraints?

  • Authors:
  • Manny Rayner;Genevieve Gorrell;Beth Ann Hockey;John Dowding;Johan Boye

  • Affiliations:
  • netdecisions, Wellington House, Cambridge, UK;netdecisions, Wellington House, Cambridge, UK;RIACS, NASA Ames Research Center, Moffett Field, CA;RIACS, NASA Ames Research Center, Moffett Field, CA;Telia Research, Farsta, Sweden

  • Venue:
  • NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

Many people are now routinely building grammar-based language models for interactive spoken language applications; these language models are typically ad hoc semantic grammars which ignore many standard linguistic constraints, in particular grammatical agreement. We describe a series of experiments in which we took three CFG-based language models from non-trivial implemented systems, and in each case contrasted the performance of a version which included agreement constraints against a version which ignored them. Our findings suggest that inclusion of agreement constraints significantly improves performance in terms of both word error rate and semantic error rate.