Abstract
This paper reports about an effort to build a large-scale call router able to reliably distinguish among 250 call reasons. Because training data from the specific application (Target) domain was not available, the statistical classifier was built using more than 300,000 transcribed and annotated utterances from related, but different, domains. Several tuning cycles including three re-annotation rounds, in-lab data recording, bag-of-words-based consistency cleaning, and recognition parameter optimization improved the classifier accuracy from 32% to a performance clearly above 70%.
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.
Similar content being viewed by others
References
Interactive Services Design Guidelines. Technical Report ITU-T Recommendation F.902, ITU, Geneva, Switzerland (1995)
Acomb, K., Bloom, J., Dayanidhi, K., Hunter, P., Krogh, P., Levin, E., Pieraccini, R.: Technical Support Dialog Systems: Issues, Problems, and Solutions. In: Proc. of the Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, Rochester, USA (2007)
Evanini, K., Suendermann, D., Pieraccini, R.: Call Classification for Automated Troubleshooting on Large Corpora. In: Proc. of the ASRU, Kyoto, Japan (2007)
Gorin, A., Riccardi, G., Wright, J.: How May I Help You? Speech Communication 23(1/2) (1997)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suendermann, D., Hunter, P., Pieraccini, R. (2008). Call Classification with Hundreds of Classes and Hundred Thousands of Training Utterances ... ... and No Target Domain Data. In: André, E., Dybkjær, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds) Perception in Multimodal Dialogue Systems. PIT 2008. Lecture Notes in Computer Science(), vol 5078. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69369-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-69369-7_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69368-0
Online ISBN: 978-3-540-69369-7
eBook Packages: Computer ScienceComputer Science (R0)