Head-driven parsing for word lattices

Authors:
Christopher Collins;Bob Carpenter;Gerald Penn
Affiliations:
University of Toronto, Toronto, ON, Canada;Alias I, Inc., Brooklyn, NY;University of Toronto, Toronto, ON, Canada
Venue:
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Year:
2004

Citing 9
Cited 5

Procedure for quantitatively comparing the syntactic coverage of English grammars

HLT '91 Proceedings of the workshop on Speech and Natural Language
Parsing N Best Trees from a Word Lattice

KI '97 Proceedings of the 21st Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Head-driven statistical models for natural language parsing

Head-driven statistical models for natural language parsing
Exploiting syntactic structure for natural language modeling

Exploiting syntactic structure for natural language modeling
Robust probabilistic predictive syntactic processing: motivations, models, and applications

Robust probabilistic predictive syntactic processing: motivations, models, and applications
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Immediate-head parsing for language models

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
A study on richer syntactic dependencies for structured language modeling

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Markov parsing: lattice rescoring with a statistical parser

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics

Improving grammaticality in statistical sentence generation: introducing a dependency spanning tree algorithm with an argument satisfaction model

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
A noisy-channel model of rational human sentence comprehension under uncertain input

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Learning word-class lattices for definition and hypernym extraction

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Spanning tree approaches for statistical sentence generation

Empirical methods in natural language generation
Syntactic language modeling with formal grammars

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present the first application of the head-driven statistical parsing model of Collins (1999) as a simultaneous language model and parser for large-vocabulary speech recognition. The model is adapted to an online left to right chart-parser for word lattices, integrating acoustic, n-gram, and parser probabilities. The parser uses structural and lexical dependencies not considered by n-gram models, conditioning recognition on more linguistically-grounded relationships. Experiments on the Wall Street Journal treebank and lattice corpora show word error rates competitive with the standard n-gram language model while extracting additional structural information useful for speech understanding.