We propose a model for a statistical representation of the conceptual structure of a restricted subset of spoken natural language. The model is used for segmenting a sentence into phrases and labeling them with concept relations (or cases). The model is trained using a corpus of annotated transcribed sentences. An understanding system is being built around this model, allowing for unconstrained spoken input in a database retrieval task. The results on a test set of 148 sentences show that almost 97% of cases were correctly assigned.
Cite as: Pieraccini, R., Levin, E. (1991) Stochastic representation of semantic structure for speech understanding. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 383-386, doi: 10.21437/Eurospeech.1991-98
@inproceedings{pieraccini91_eurospeech,
author={Roberto Pieraccini and Esther Levin},
title={{Stochastic representation of semantic structure for speech understanding}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={383--386},
doi={10.21437/Eurospeech.1991-98}
}