|
Abstract : |
This paper investigates the impact of Constraint Dependency Grammars (CDG) on the accuracy of an integrated speech recognition and CDG pars-ing system. We compare a conventional CDG with CDGs that are induced from annotated sentences and template-expanded sentences. The grammars are evaluated on parsing speed, precision/coverage, and improvement of word and sentence accuracy of the integrated system. Sentence-derived CDGs sig-nificantly improve recognition accuracy over the con-ventional CDG but are less general. Expanding the sentences with templates provides us with a mech-anism for increasing the coverage of the grammar with only minor reductions in recognition accuracy. 1, |
