Abstract
The design rationale guiding the development of the reductionist dialog act based translation module in Verbmobil was robustness. Even in case the speech recognition or the prosodic processing does not perform perfectly, this module extracts and translates the main intentions and facts related to the domain. In a three step approach, first the dialog act describing the intention is computed using a statistical approach. The second step is the construction of the propositional content with robust hierarchical finite state transducers. For the definition of the transducers, knowledge sources available in Verbmobil are exploited. The resulting representation of these two steps is used in a template based finite state generator to realize the target language expressions. The internal representation is also communicated to the dialog module where it plays an important part in maintaining the dialog state.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Alexandersson, J., Buschbeck-Wolf, B., Fujinami, T., Kipp, M., Koch, S., Maier, E., Reithinger, N., Schmitz, B., and Siegel, M. (1998). Dialogue Acts in VERBMOBIL-2, Second Edition. Verbmobil-Report 226, DFKI Saarbrücken, Universität Stuttgart, Technische Universität Berlin, Universität des Saarlandes.
Alexandersson, J., Poller, P., and Kipp, M. Generating Multilingual Dialog Summaries and Minutes. In this volume.
Alexandersson, J., Engel, R., Kipp, M., Koch, S., Küssner, U., Reithinger, N., and Stede, M. Modeling Negotiation Dialogs. In this volume.
Appelt, D., Hobbs, J., Bear, J., and Tyson, M. (1993). FASTUS: A Finite-State Processor for Information Extraction from Real-World Text. In Proceedings of the International Joint Conference on Artificial Intelligence.
Batliner, A., Buckow, J., Niemann, H., Nöth, E., and Warnke, V. The Prosody Module. In this volume.
Block, H. U. (1997). The Language Components in Verbmobil. In Proceedings of the International Conference on Acoustics, Signal and Speech Processing, 79–82.
Burger, S., Weilhammer, K., Tillmann, H., and Schiel, F. Verbmobil Data Collection and Annotation. In this volume.
Choi, W. S. Jeon-Mi-Cho, and Seo, J. (1999). Analysis System of Speech Acts and Disourse Structures Using Maximum Entropy Model. In Proceedings of Association of Computational Linguistics, 230–237.
Corazza, A. (1999). An Inter-Domain Portable Approach to Interchange Format Construction. In Proceedings of EuroSpeech-99, 2419–2426.
Gibbon, D., and Lüngen, H. Speech Lexica and Consistent Multilingual Vocabularies. In this volume.
Kipp, M. (1998). The Neural Path to Dialogue Acts. In Proceedings of the European Conference on Artificial Intelligence, 175–179.
Kipp, M., Alexandersson, J., Reithinger, N., and Engel, R. Dialog Processing. In this volume.
Klesen, M. (1997). Statistische Klassifikation von Dialogakten. Master’s thesis, Universität des Saarlandes, Saarbrücken.
Koch, S., Kipp, M., Alexandersson, J., Engel, R., Reithinger, N., Küssner, U., and Stede, M. Modeling Negotiation Dialogs. In this volume.
Mast, M., Niemann, H., Nöth, E., and Schukat-Talamazzini, E. G. (1995). Automatic Classification of Dialog Acts with Semantic Classification Trees and Polygrams. International Joint Conference on Artificial Intelligence, Workshop on Machine Learning, Montreal.
Reithinger, N., and Klesen, M. (1997). Dialogue Act Classification Using Language Models. In Proceedings of EuroSpeech-97, 2235–2238.
Reithinger, N., Engel, R., Kipp, M., and Klesen, M. (1996). Predicting Dialogue Acts for a Speech-To-Speech Translation System. In Proceedings of the International Conference on Speech and Language Processing, 654–657.
Samuel, K., Carberry, S., and Vijay-Shanker, K. (1998). Computing Dialogue Acts from Features with Transformation-Based Learning. In Proceedings of the American Association for Artificial Intelligence, 90–97.
Tanaka, H., and Yokoo, A. (1999). An Efficient Statistical Speech Act Type Tagging System for a Speech Translation System. In Proceedings of the Association for Computational Linguistics, 381–388.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Reithinger, N., Engel, R. (2000). Robust Content Extraction for Translation and Dialog Processing. In: Wahlster, W. (eds) Verbmobil: Foundations of Speech-to-Speech Translation. Artificial Intelligence. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-04230-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-662-04230-4_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08730-1
Online ISBN: 978-3-662-04230-4
eBook Packages: Springer Book Archive