An Iterative Growing and Pruning Algorithm for Classification Tree Design
IEEE Transactions on Pattern Analysis and Machine Intelligence
A tree-based statistical language model for natural language speech recognition
Readings in speech recognition
Stochastic representation of conceptual structure in the ATIS task
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
Evaluation of spoken language systems: the ATIS domain
HLT '90 Proceedings of the workshop on Speech and Natural Language
Speech understanding in open tasks
HLT '91 Proceedings of the workshop on Speech and Natural Language
Fragment processing in the DELPHI system
HLT '91 Proceedings of the workshop on Speech and Natural Language
Robust parsing for spoken language systems
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
| Hi-index | 0.00 |
Many speech understanding systems look for keywords in an utterance to build a semantic representation. Keyword Classification Trees (KCTs) learn keyword-based semantic rules from training data, eliminating much hand-coding of linguistic rules previously considered necessary. Given labelled training sentences, a KCT automatically chooses keywords from the lexicon and learns semantic rules based on regular expressions consisting of these keywords and gaps (substrings of unspecified length made up of non-keywords). A linguistic analyzer based on KCTs was trained on sentences from the ATIS air travel task and incorporated into the system built at CRIM for the November 1992 ATIS benchmarks. Word sequences were processed by a local parser that identified semantically important noun phrases and then passed through a forest of KCTs, each responsible for generating a different aspect of the semantic representation.