Abstract
The insufficiency in methods for generating utterances still remains as a critical issue unsolved in the community of non-task-oriented conversation. Previous studies provide various strategies to enrich the methods for generating utterances, thus making the conversation systems or agents appear more interesting. However, none of them could escape from the fact that they all generate utterances depending mainly on some particular kinds of templates or augmented templates. We propose here in this paper a thorough modification to a preceding work to address this problem. Specifically, we first introduce a concept Utterance Window to strengthen the association between continuous utterances, and then employ a Two-starting-word Markov connection to cope with the ease of losing focus of the current utterance. In addition, we try to keep tract of user’s interests and reflecting them in the process of topic-word extraction and utterance generation as well. The experimental results show the effectiveness of our method.
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
Fujimoto, E., Takanashi, K., Kono, Y., Kidoe, M.: An Analysis of Topic Changes in Free Conversation Using Conceptual Relations. In: Proceedings of the 18th Annual Conference of the Japanese Society for Artificial Intelligence, 2G3-01 (2004) (in Japanese)
Saito, T., Hirota, K., Hoshino, J.: Utterance and Small Talk Model between Characters by Using Web Information. SIG notes, NL-2007(181), Information Processing Society of Japan, pp. 53–58 (2007) (in Japanese)
Higuchi, S., Rzepka, R., Araki, K.: A Casual Conversation System Using Modality and Word Associations Retrieved from the Web. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pp. 382–390 (2008)
Yoshioka, K., Yoshimura, E., Watabe, H., Kawaoka, T.: Computer Conversational Processing System Based on Individuality and Personal Preference Information. In: Proceedings of FIT 2008, vol. (2), pp. 289–290 (2008)
Song, X., Maeda, K., Kunimasa, H., Toyota, H., Han, D.: Topic Control in A Free Conversation System. In: Proceedings of the 2009 IEEE International Conference on Natural Language Processing and Knowledge Engineering, pp. 529–534 (2009)
Han, D., Song, X., Maeda, K.: Topic Presentation for a Free Conversation System Based on the Web Texts. International Journal of Digital Content Technology and its Applications 4(3), 7–14 (2010)
Takahashi, M., Rzepka, R., Araki, K.: Improving Utterance Generation Method Based on Word Ngrams. In: Joint Convention Record, the Hokkaido Chapters of the Institute of Electrical and Information Engineers, vol. 112 (2009) (in Japanese)
Han, D., Kinoshita, Y., Fukuchi, R., Kousaki, T.: Utterance Generation Using Twitter Replying Sentences and Character Assignment. International Journal of Digital Content Technology and its Applications 5(10), 119–126 (2011)
Kurohahsi, S., Shiraki, N., Nagao, M.: A Method for Detecting Important Descriptions of a Word Based on Its Density Distribution in Text. Transactions of Information Processing Society of Japan 38(4), 845–854 (1997) (in Japanese)
Satake, S., Kawashima, H., Imai, M.: Contents Selection Method Based on A User Interest on the Interactive News Announcer Robot. Technical Report of IEICE, DE-2005(50), pp. 119-124 (2005) (in Japanese)
Church, K., Hanks, P.: Word association norms, mutual information, and lexicography. Computational Linguistics 16(1), 22–29 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nishio, Y., Han, D. (2012). Automatic Utterance Generation by Keeping Track of the Conversation’s Focus within the Utterance Window. In: Isahara, H., Kanzaki, K. (eds) Advances in Natural Language Processing. JapTAL 2012. Lecture Notes in Computer Science(), vol 7614. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33983-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-33983-7_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33982-0
Online ISBN: 978-3-642-33983-7
eBook Packages: Computer ScienceComputer Science (R0)