Abstract
We present a supervised machine learning approach for detecting problematic human-computer dialogs between callers and an automated agent in a call center. The proposed model can distinguish problematic from non-problematic calls after only five caller turns with an accuracy of over 90%. Based on a corpus of more than 69,000 dialogs we further employ the classifier’s decision to given business models and present the cost savings that can be achieved by deploying classification techniques to Interactive Voice Response systems.
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
Cohen, W.W., Singer, Y.: A simple, fast, and effective rule learner. In: Proceedings of the Sixteenth National Conference of Artificial Intelligence (1999)
Horvitz, E., Paek, T.: Complementary computing: policies for transferring callers from dialog systems to human receptionists. User Modeling and User-Adapted Interaction 17(1-2), 159–182 (2007)
Kim, W.: Online call quality monitoring for automating agent-based call centers. In: Proceedings Interspeech 2007 ICSLP, Antwerp, Belgium (2007)
Levin, E., Pieraccini, R.: Value-based optimal decision for dialog systems. In: Workshop on Spoken Language Technologies (SLT 2006), Aruba (2006)
Walker, M., Langkilde, I., Wright, J., Gorin, A., Litman, D.: Learning to predict problematic situations in a spoken dialogue system: Experiments with how i help you. In: Proceedings of the first conference on North American chapter of the Association for Computational Linguistics (2000a)
Walker, M., Langkilde-Geary, I., Wright, H., Wright, J., Gorin, A.: Automatically training a problematic dialogue predictor for a spoken dialogue system. Journal of Artificial Intelligence Research 16, 293–319 (2002)
Walker, M., Wright, J., Langkilde, I.: Using natural language processing and discourse features to identify understanding errors in a spoken dialogue system. In: Proc. 17th International Conf. on Machine Learning, pp. 1111–1118. Morgan Kaufmann, San Francisco (2000b)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schmitt, A., Hank, C., Liscombe, J. (2008). Detecting Problematic Dialogs with Automated Agents. 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_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-69369-7_9
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)