Bi-directional LR parsing from an anchor word for speech recognition

Authors:
Hiroaki Saito
Affiliations:
Carnegie Mellon University, Pittsburgh, PA
Venue:
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Year:
1990

Citing 4
Cited 1

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
Parsing spoken language: a semantic caseframe approach

COLING '86 Proceedings of the 11th coference on Computational linguistics
Robust parsing of severely corrupted spoken utterances

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 1
Parsing noisy sentences

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2

Linear-time suffix parsing for deterministic languages

Journal of the ACM (JACM)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new technique of parsing sentences from an arbitrary word which is highly reliable or semantically important. This technique adopts an efficient LR parsing method and uses a reverse LR table constructed besides a standard LR table. This technique is particularly suitable in parsing a lattice of words hypothesized by a speech recognition module. If we choose anchor symbols in such a way that they are almost always acoustically reliable, the bi-directional LR parsing performs better against misrecognized words than the regular left-to-right LR parser, while most of the LR efficiency is preserved. A pilot implementation shows a 43% reduction of the error rate against the left-to-right LR method in parsing the speech input.