Abstract
Over the last few years, stochastic models have been widely used in the natural language understanding modeling. Almost all of these works are based on the definition of segments of words as basic semantic units for the stochastic semantic models.
In this work, we present a two—level stochastic model approach to the construction of the natural language understanding component of a dialog system in the domain of database queries. This approach will treat this problem in a way similar to the stochastic approach for the detection of syntactic structures (Shallow Parsing or Chunking) in natural language sentences; however, in this case, stochastic semantic language models are based on the detection of some semantic units from the user turns of the dialog. We give the results of the application of this approach to the construction of the understanding component of a dialog system, which answers queries about a railway timetable in Spanish.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
A. Bonafonte, P. Aibar, N. Castell, E. Lleida, J.B. Mari no, E. Sanchis, and M.I. Torres. Desarrollo de un sistema de diálogo oral en dominios restringidos. In Proceedings of I Jornadas en Tecnología del Habla, 2000.
T. Brants. Cascaded Markov Models. In Proceedings of the EACL99, Bergen, Norway, 1999.
P. Clarksond and R. Ronsenfeld. Statistical Language Modeling using the CMU-Cambridge Toolkit. In Proceedings of Eurospeech, Rhodes, Greece, 1997.
S. M. Katz. Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recognizer. IEEE Transactions on Acoustics, Speech and Signal Processing, 35, 1987.
L. Lamel, S. Rosset, J. Gauvain, S. Bennacef, M. Garnier-Rizet, and B. Prouts. The LIMSI ARISE System. Speech Communication, 31(4):339–353, 2000.
E. Levin and R. Pieraccini. Concept-Based Spontaneous Speech Understanding System. In Proceedings of EUROSPEECH’95, pages 555–558, 1995.
W. Minker. Stocastically—Based Semantic. Analysis for ARISE — Automatic Railway Information Systems for Europe. 2(2):127–147, 1999.
F. Pla, A. Molina, and N. Prieto. Tagging and Chunking with Bigrams. In Proceedings of the COLING— 2000, Saarbrücken, Germany, August 2000.
F. Pla, A. Molina, and N. Prieto. An Integrated Statistical Model for Tagging and Chunking Unrestricted Text. In Proceedings of the Text, Speech and Dialogue 2000, Brno, Czech Republic, September 2000.
F. Pla, A. Molina, and N. Prieto. Improving Chunking by means of Lexical-Contextual Information in Statistical Language Models. In Proceedings of 4th CoNLL-2000 and LLL-2000, Lisbon, Portugal, September 2000.
E. Sanchis, E. Segarra, M. Galiano, F. García, and L. Hurtado. Modelización de la Compresión mediante Técnicas de Aprendizaje Automático. In Proceedings of I Jornadas en Tecnología del Habla, 2000.
R. Schwartz, S. Miller, D. Stallard, and J. Makhoul. Language Understanding using hidden understanding models. In ICSLP, pages 997–1000, 1996.
E. Segarra, V. Arranz, N. Castell, I. Galiano, F. García, A. Molina, and E. Sanchis. Representación Semántica de la Tarea. In Internal Report UPV DSIC-II/5/00, 2000.
E. Segarra, E. Sanchis, M. Galiano, F. García, and L. Hurtado. Extracting Semantic Information through Automatic Learning Techniques. In IX Spanish Symposium on Pattern Recognition and Image Analysis-SNRFAI’ 01, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pla, F., Molina, A., Sanchis, E., Segarra, E., García, F. (2001). Language Understanding Using Two-Level Stochastic Models with POS and Semantic Units. In: Matoušek, V., Mautner, P., Mouček, R., Taušer, K. (eds) Text, Speech and Dialogue. TSD 2001. Lecture Notes in Computer Science(), vol 2166. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44805-5_54
Download citation
DOI: https://doi.org/10.1007/3-540-44805-5_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42557-1
Online ISBN: 978-3-540-44805-1
eBook Packages: Springer Book Archive