Abstract
This paper presents automatic methods for the classification of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the utterances are analyzed in depth and for the rest, shallow processing takes place. The dialog component keeps track of the dialog with this shallow processing. For the classification of utterances without in depth processing two methods are presented: Semantic Classification Trees and Polygrams. For both methods the classification algorithm is trained automatically from a corpus of labeled data. The novel idea with respect to SCTs is the use of dialog state dependent CTs and with respect to Polygrams it is the use of competing language models for the classification of dialog acts.
This work was funded by the German Federal Ministry of Education, Science, Research and Technology (BMBF) in the framework of the Verbmobil Project under Grant 01 IV 102 H/0. The responsibility for the contents of this study lies with the authors. The authors wish to thank R. Kuhn for providing the SCT software.
Preview
Unable to display preview. Download preview PDF.
References
J. Alexandersson, E. Maier, and N. Reithinger. A robust and efficient three-layered dialogue component for a speech-to-speech translation system. In EACL 1995, to appear 1995.
J. Fischer. Integrierte Erkennung von Phrasengrenzen und Phrasenakzenten mit Klassifikationsbäumen. Diplomarbeit, Lehrstuhl für Mustererkennung (Informatik 5), Universität Erlangen-Nürnberg, 1994.
S. Gelfand, C. Ravishankar, and E. Delp. An Iterative Growing and Pruning Algorithm for Classification Tree Design. IEEE Trans. on Pattern Analysis and Machine Intelligence, 13:302–320, Februar 1991.
F. Jelinek. Self-Organized Language Modeling for Speech Recognition. In A. Waibel and K.F. Lee, editors, Readings in Speech Recognition, pages 450–506. Morgan Kaufmann, San Mateo, CA, 1990.
F. Jelinek and R.L. Mercer. Interpolated Estimation of Markov Source Parameters from Sparse Data. In E.S. Gelsema and L.N. Kanal, editors, Pattern Recognition in Practice, pages 381–397. North Holland, 1980.
S. Katz. Estimation of Probability from Sparse Data for the Language Model Component at a Speech Recognizer. IEEE Trans. on Acoustics, Speech and Signal Processing, ASSP-35(3):400–401, 1987.
S. Kameyama and I. Maleck. Konstellation und Szenario von Terminabsprachen, Verbmobil-Report-23-93, Dezember 1993.
T. Kuhn, H. Niemann, and E.G. Schukat-Talamazzini. Ergodic Hidden Markov Models and Polygrams for Language Modeling. In Proc. Int. Conf. on Acoustics, Speech and Signal Processing, volume 1, pages 357–360, Adelaide, Australia, 1994.
R. Kuhn. Keyword Classification Trees for Speech Understanding Systems. Technical report, CRIM, Montreal, Canada, 1992.
E. Maier, editor. Dialogmodellierung in VERBMOBIL — Festlegung der Sprechhandlungen für den Demonstrator Verbmobil-Memo-31-94. Juli 1994.
L.R. Rabiner. Mathematical Foundations of Hidden Markov Models. In H. Niemann, M. Lang, and G. Sagerer, editors, Recent Advances in Speech Understanding and Dialog Systems, volume 46 of NATO ASI Series F, pages 183–205. Springer-Verlag, Berlin, 1988.
E.G. Schukat-Talamazzini, R. Hendrych, R. Kompe, and H. Niemann. Permugram language models. In Proc. European Conf. on Speech Communication and Technology, volume 3, pages 1773–1776, Madrid, September 1995.
E.G. Schukat-Talamazzini, T. Kuhn, and H. Niemann. Speech Recognition for Spoken Dialogue Systems. In Niemann, de Mori, and Hanrieder, editors, Progress and Prospects of Speech Research and Technology: Proc. of the CRIM/FORWISS Workshop (München, Sept. 1994), pages 110–120, Sankt Augustin, 1994. infix.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mast, M., Niemann, H., Nöth, E., Schukat-Talamazzini, E.G. (1996). Automatic classification of dialog acts with Semantic Classification Trees and Polygrams. In: Wermter, S., Riloff, E., Scheler, G. (eds) Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing. IJCAI 1995. Lecture Notes in Computer Science, vol 1040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60925-3_49
Download citation
DOI: https://doi.org/10.1007/3-540-60925-3_49
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60925-4
Online ISBN: 978-3-540-49738-7
eBook Packages: Springer Book Archive