An efficient chart-based algorithm for partial-parsing of unrestricted texts
ANLC '92 Proceedings of the third conference on Applied natural language processing
Inside-outside reestimation from partially bracketed corpora
HLT '91 Proceedings of the workshop on Speech and Natural Language
Parameter estimation for constrained context-free language models
HLT '91 Proceedings of the workshop on Speech and Natural Language
A relaxation method for understanding spontaneous speech utterances
HLT '91 Proceedings of the workshop on Speech and Natural Language
| Hi-index | 0.00 |
While statistically based Markov-chain language models (N-gram models) have been shown to be effective for speech recognition, there is, in general, more stmcture present in natural language than N-gram models can capture. Linguistically based approaches that use statistics to provide probabilities for word sequences that are accepted by a grammar, typically require a full coverage grammar, and therefore are only useful for constrained sublanguages. In the work presented here, we combine linguistic structure in the form of a partial-coverage phrase structure grammar with statistical N-gram techniques. The result is a robust statistical grammar which explicitly incorporates linguistic and semantic structure. We are applying this approach to the recognition of air-traffic-control transmissions and have already shown that a simpler hybrid approach is useful. This work extends those preliminary results to a more general framework.