TINA: a probabilistic syntactic parser for speech understanding systems
HLT '89 Proceedings of the workshop on Speech and Natural Language
Speech recognition in SRI's resource management and ATIS systems
HLT '91 Proceedings of the workshop on Speech and Natural Language
Stochastic representation of conceptual structure in the ATIS task
HLT '91 Proceedings of the workshop on Speech and Natural Language
Augmented role filling capabilities for semantic interpretation of spoken language
HLT '91 Proceedings of the workshop on Speech and Natural Language
A template matcher for robust NL interpretation
HLT '91 Proceedings of the workshop on Speech and Natural Language
Interactive problem solving and dialogue in the ATIS domain
HLT '91 Proceedings of the workshop on Speech and Natural Language
Evaluation of spoken language systems: the ATIS domain
HLT '90 Proceedings of the workshop on Speech and Natural Language
The CMU air travel information service: understanding spontaneous speech
HLT '90 Proceedings of the workshop on Speech and Natural Language
Syntactic and semantic knowledge in the DELPHI unification grammar
HLT '90 Proceedings of the workshop on Speech and Natural Language
Integration of speech recognition and natural language processing in the MIT VOYAGER system
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Learning speech semantics with keyword classification trees
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Spoken dialogue in virtual worlds
COST'09 Proceedings of the Second international conference on Development of Multimodal Interfaces: active Listening and Synchrony
Hi-index | 0.00 |
This paper describes a recent extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a full linguistic analysis fails. This "robust" parsing capability was achieved through minor extensions of pre-existing components already in place for the full linguistic analysis component. Robust parsing is applied only after a full analysis has failed, and it involves the two stages of 1) parsing a set of phrases and clauses, and 2) gluing them together to obtain a single semantic frame encoding the full meaning of the sentence. In a recent evaluation on text input collected at multiple sites within the DARPA community, less than two thirds of the sentences yielded a full parse, but the overwhelming majority of the remaining sentences were analyzed correctly by the robust parsing scheme. We also analyzed the results when text input was replaced by recognizer outputs [3]. Even though the recognizer produced greater than 50% sentence error rate, the drop in score (%correct - %incorrect) was only 10 percentage points. This result leads to the conclusion that most of the recognizer errors are harmless in terms of meaning analysis, as long as a robust mechanism for accounting for the parsable phrases is in place.