Learning speech semantics with keyword classification trees

A linguistic analyzer based on KCTs (keyword classification trees) was trained on sentences from the ATIS (Air Travel Information System) air travel task and incorporated into the system (CHANEL) built at CRIM (Centre de Recherche Informatique de Montreal) for the Nov. 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. CHANEL attained a reasonable performance level, despite its heavy reliance on KCTs rather than on handcoded linguistic rules. The CRIM speech recognition system had a recognition rate of 88.9% words correct; CHANEL is clearly robust.<<ETX>>

[1]  Mei-Yuh Hwang,et al.  Speech Understanding in Open Tasks , 1992, HLT.

[2]  David Stallard,et al.  Fragment Processing in the DELPHI System , 1992, HLT.

[3]  Douglas E. Appelt,et al.  A Template Matcher for Robust NL Interpretation , 1991, HLT.

[4]  Edward J. Delp,et al.  An Iterative Growing and Pruning Algorithm for Classification Tree Design , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Chin-Hui Lee,et al.  Stochastic Representation of Conceptual Structure in the ATIS Task , 1991, HLT.

[6]  P. J. Price,et al.  Evaluation of Spoken Language Systems: the ATIS Domain , 1990, HLT.

[7]  Edward J. Delp,et al.  An iterative growing and pruning algorithm for classification tree design , 1989, Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics.

[8]  Stephanie Seneff.  Robust parsing for spoken language systems , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Stuart L. Crawford,et al.  Classification Trees for Information Retrieval , 1991, ML.

[10]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .