Abstract
Extrapositions are discontinuous constructions of spontaneous speech where constituents are extraposed into the Nachfeld. Parallelism constraints between the source sentence and the extraposed constituents are claimed to govern all possible interpretations induced by an extra-posed constituent. The aim of this article is to integrate visual context information into the parsing model to avoid possible overgeneralizations which might arise from contradictory information given by the source sentence and the extraposed constituent. Therefore, a careful approach to uncertainty is needed because the system is concerned with erroneous, vague, and incomplete data from vision and speech recognition. Bayesian Networks provide an adequate environment to model these uncertain¬ties. The conditional probabilities of the Network are estimated from psycholinguistic experiments.
This work has been supported by the German Reasearch Foundation (DFG) within SFB 360.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Gemot A. Fink. Developing HMM-based recognizers with ESMERALDA. In Workshop on Text, Speech, and Dialog, Pilsen, Czech Republic, September 1999. to appear.
G. Heidemann, F. Kümmert, H. Ritter, and G. Sagerer. A Hybrid Object Recognition Architecture. In C. von der Malsburg, W. von Seelen, J.C. Vorbrüggen, and B. Sendhoff, editors, Artificial Neural Networks - ICANN 96, 16.–19. July, pages 305–310. Springer-Verlag, Berlin, 1996.
F. Kümmert, G.A. Fink, G. Sagerer, and E. Braun. Hybrid Object Recognition in Image Sequences. In 14th International Conference on Pattern Recognition, volume II, pages 1165–1170, Brisbane, 1998.
S. Kronenberg and F. Kümmert. Syntax coordination: Interaction of discourse and extrapositions. In ICSLP, volume 5, pages 2071–2074, Sydney, Australia, 1998.
S. Kronenberg and F. Kümmert. Soft unification: Towards robust parsing of spantaneous speech. In IASTED International Conference on Artificial Intelligence and Soft Computing, 9–12. August 1999, Honolulu,USA, 1999. to appear.
S. Kronenberg and F. Kümmert. Syntactic disambiguation of extrapositions. In IASTED International Conference on Artificial Intelligence and Soft Computing, 9.–12. August 1999, Honolulu,US A, 1999. to appear.
A. Maßmann, S. Posch, and D. Schlüter. Using markov random fields for contour-based grouping. In Proc. of Int. Conf. on Image Processing, volume 2, pages 207–242, 1997.
Judea Pearl. Probabilstic reasoning in intelligent systems: networks of plausi ble inference. Morgan Kaufmann, 1989.
G. Socher, T. Merz, and S. Posch. 3-D Reconstruction and Camera Calibration from Images with Known Objects. In D. Pycock, editor, Proc. 6th British Machine Vision Conference, pages 167–176, 1995.
G. Socher, G. Sagerer, and P. Perona. Baysian Reasoning on Qualitative Descriptions from Images and Speech. In H. Buxton and A. Mukerjee, editors, ICCV’98 WS on Conceptual Description of Images, 1998.
S. Wachsmuth, H. Brandt-Pook, G. Socher, F. Kümmert, and G. Sagerer. Multilevel integration of vision and speech understanding using bayesian networks. In H. I. Christensen, editor, Computer Vision Systems: First International Conference, volume 1542 of Lecture Notes in Computer Sci-ence, pages 231–254, Las Palmas, Spain, January 1999. Springer-Verlag.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kronenberg, S., Wachsmuth, S., Kummert, F., Sagerer, G. (1999). Disambiguation of Utterances by Visual Context Information. In: Förstner, W., Buhmann, J.M., Faber, A., Faber, P. (eds) Mustererkennung 1999. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60243-6_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-60243-6_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66381-2
Online ISBN: 978-3-642-60243-6
eBook Packages: Springer Book Archive