Abstract
In this paper, we are interested in the problem of understanding human conversation structure in the context of human-agent and human-human interaction. We present a statistical methodology for detecting the structure of spoken dialogs based on a generative model learned using decision trees. To evaluate our approach we have used a dialog corpus collected from real users engaged in a problem solving task. The results of the evaluation show that automatic segmentation of spoken dialogs is very effective not only with models built using separately human-agent dialogs or human-human dialogs, but it is also possible to infer the task-related structure of human-human dialogs with a model learned using only human-agent dialogs.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Hearst, M.: Multi-paragraph segmentation of expository text. In: Proc. ACL, pp. 9–16 (1994)
Yamron, J.: Topic detection and tracking segmentation task. In: Proc. Broadcast News Transcription and Understanding Workshop (1998)
Ponte, J., Croft, W.: Text segmentation by topic. In: Peters, C., Thanos, C. (eds.) ECDL 1997. LNCS, vol. 1324, pp. 113–125. Springer, Heidelberg (1997)
Passoneau, R., Litman, D.: Discourse segmentation by human and automated means. Computational Linguistics 23, 103–139 (1997)
Angheluta, R., Busser, R.D., Moens, M.: The use of topic segmentation for automatic summarization. In: Proc. ACL Workshop on Automatic Summarization, pp. 66–70 (2002)
Walker, M.A.: Centering, anaphora resolution, and discourse structure, pp. 401–435. Oxford University Press (1998)
Chai, J., Jin, R.: Discourse structure for context question answering. In: Proc. HLT-NAACL Workshop on Pragmatics of Question Answering, pp. 23–30 (2004)
Doran, C., Aberdeen, J., Damianos, L., Hirschman, L.: Comparing several aspects of human-computer and human-human dialogues. In: Proc. SigDial (2001)
Bangalore, S., Fabbrizio, G.D., Stent, A.: Learning the Structure of Task-driven Human-Human Dialogs. IEEE Trans. Audio Speech Lang. Processing 16(7), 1249–1259 (2008)
Griol, D., Molina, J., Callejas, Z.: Bringing together commercial and academic perspectives for the development of intelligent AmI interfaces. JAISE 4(3), 183–207 (2012)
Stepanov, E., Riccardi, G., Bayer, A.: The Development of the Multilingual LUNA Corpus for Spoken Language System Porting. In: Proc. LREC, pp. 2675–2678 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Griol, D., Molina, J.M. (2015). Do Human-Agent Conversations Resemble Human-Human Conversations?. In: Omatu, S., et al. Distributed Computing and Artificial Intelligence, 12th International Conference. Advances in Intelligent Systems and Computing, vol 373. Springer, Cham. https://doi.org/10.1007/978-3-319-19638-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-19638-1_18
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19637-4
Online ISBN: 978-3-319-19638-1
eBook Packages: EngineeringEngineering (R0)