Advertisement

Cluster Computing

, Volume 19, Issue 4, pp 2315–2326 | Cite as

A novel density-based clustering method using word embedding features for dialogue intention recognition

  • Jungsun Jang
  • Yeonsoo Lee
  • Seolhwa Lee
  • Dongwon Shin
  • Dongjun Kim
  • Haechang Rim
Article

Abstract

In dialogue systems, understanding user utterances is crucial for providing appropriate responses. Various classification models have been proposed to deal with natural language understanding tasks related to user intention analysis, such as dialogue acts or emotion recognition. However, models that use original lexical features without any modifications encounter the problem of data sparseness, and constructing sufficient training data to overcome this problem is labor-intensive, time-consuming, and expensive. To address this issue, word embedding models that can learn lexical synonyms using vast raw corpora have recently been proposed. However, the analysis of embedding features is not yet sufficient to validate the efficiency of such models. Specifically, using the cosine similarity score as a feature in the embedding space neglects the skewed nature of the word frequency distribution, which can affect the improvement of model performance. This paper describes a novel density-based clustering method that efficiently integrates word embedding vectors into dialogue intention recognition. Experimental results show that our proposed model helps overcome the data sparseness problem seen in previous classification models and can assist in improving the classification performance.

Keywords

Dialogue Act Emotion recognition Density-based clustering Word embedding 

References

  1. 1.
    Mancini, M., Pelachaud, C.: Dynamic behavior qualifiers for conversational agents. In: Intelligent Virtual Agents: 7th International Working Conference, pp. 112–124 (2007)Google Scholar
  2. 2.
    Bosma, W., André, E.: Exploiting emotions to disambiguate dialogue acts. In: Proceedings of the 9th International Conference on Intelligent User Interfaces, pp. 85–92 (2004)Google Scholar
  3. 3.
    Austin, J.A.: How to Do Things with Words. Harvard University Press, Cambridge (1962)Google Scholar
  4. 4.
    Traum, D., Larsson, S.: The information state approach to dialogue management. In: Smith, R., van Kuppevelt, J. (eds.) Current and New Directions in Discourse and Dialogue. Kluwer, Dordrecht (2003)Google Scholar
  5. 5.
    Bub, T., Schwinn, J.: VERBMOBIL: the evolution of a complex large speech-to-speech translation system. In: Proceedings of International Conference on Spoken Language Processing, (1996)Google Scholar
  6. 6.
    Allen, J., Core, M.: DAMSL: dialogue act markup in several layers (draft 2.1). Technical Report, University of Rochester, (1997)Google Scholar
  7. 7.
    Bunt, H., Alexandersson, J., Charletta, J., Choe, J.W., Fang, A.C., Hasida, K., Lee, K., Petukhova, V., Popescu-Belis, A., Romary, L., Soria, C., Traum, D.: Towards an ISO standard for dialogue act annotation. In: Proceedings of International Language Resources and Evaluation (LREC’10), pp. 2248–2558, (2010)Google Scholar
  8. 8.
    Bunt, H., Alexandersson, J., Charletta, J., Choe, J.W., Fang, A.C., Hasida, K., Lee, K., Petukhova, V., Popescu-Belis, A., Romary, L., Soria, C., Traum, D.: ISO 24617-2: a semantically-based standard for dialogue annotation. In;: Proceedings of International Language Resources and Evaluation (LREC’12), pp. 430–437, (2012)Google Scholar
  9. 9.
    Lee, H., Kim, H., Seo, J.: An effective two-step model for speech act analysis in a schedule management domain. Korean J. Cognit. Sci. 19(3), 297–310 (2008)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kim, S., Lee, Y., Lee, J.: Korean speech act tagging using previous sentence features and following candidate speech acts. J. Korean Inst. Inform.n Sci. Eng. 35(6), 374–385 (2008)Google Scholar
  11. 11.
    Kim, M., Park, J., Kim, S., Rim, H., Lee, D.: A comparative study on optimal feature identification and combination for Korean dialogue act classification. J. Korean Inst. Inform.n Sci. Eng. 35(11), 681–691 (2008)Google Scholar
  12. 12.
    Kim, H., Seon, C., Seo, J.: Review of Korean speech act classification: machine learning methods. J. Comput. Sci. Eng. 5(4), 288–293 (2011)CrossRefGoogle Scholar
  13. 13.
    Aman, S., Szpakowicz, S.: Identifying expressions of emotion in text. In: Proceedings of 10th International Conference on Text, Speech and Dialogue, (2007)Google Scholar
  14. 14.
    Valstar, M., Jiang, B., Méhu, M., Pantic, M., Scherer, K.: The first facial expression recognition and analysis challenge. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 921–926, (2011)Google Scholar
  15. 15.
    Alhussein, M.: Automatic facial emotion recognition using weber local descriptor for e-Healthcare system. Clust. Comput. 19(1), 99–108 (2016)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Purver, M., Battersby, S.: Experimenting with distant supervision for emotion classification. In: Proceedings of EACL, pp. 482–491 (2012)Google Scholar
  17. 17.
    Kang, S., Park, H., Seo, J.: Emotion classification of user’s utterance for a dialogue system. Korean J. Cognit. Sci. 21(4), 459–480 (2010)CrossRefGoogle Scholar
  18. 18.
    Hasegawa, T., Kaji, N., Yoshinaga, N., Toyoda, M.: Predicting and eliciting addressee’s emotion in online dialogue. In: Proceedings of ACL, pp. 964–972, (2013)Google Scholar
  19. 19.
    Plutchik, R.: A general psychoevolutionary theory of emotion. In: Plutchik, R., Kellerman, H. (eds.) Emotion: Theory, Research, and Experience, pp. 3–33. Academic Press, New York (1980)CrossRefGoogle Scholar
  20. 20.
    Dumais, S.T.: Latent semantic analysis. Ann. Rev. Inform. Sci. Technol. 38, 188–230 (2004)CrossRefGoogle Scholar
  21. 21.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)MATHGoogle Scholar
  22. 22.
    Mikolov, T., Karafiat, M., Burget, L., Cernocky, J.: Recurrent neural network based language model. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010), pp. 1045–1048, (2010)Google Scholar
  23. 23.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at ICLR, (2013)Google Scholar
  24. 24.
    Barnoi, M., Dinu, G., Kruszewski, G.: Don’t count, predict! a systematic comparison of context-counting versus context-predicting semantic vectors. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 238–247, (2014)Google Scholar
  25. 25.
    Xu, R., Chen, T., Xia, Y., Lu, Q., Liu, B., Wang, X.: Word embedding composition for data imbalances in sentiment and emotion classification. Cognit. Comput. 7(2), 226–240 (2015)CrossRefGoogle Scholar
  26. 26.
    Shin, D., Lee, Y., Jang, J., Rim, H.: Emotion classification in dialogue using embedding features. In: Proceedings of the 27th Conference on Hangul and Korean Language Information Processing, pp. 109–114, (2015)Google Scholar
  27. 27.
    Aggarwal, C.C., Reddy, C.K.: Data Clustering Algorithms and Applications. CRC Press, Boca Raton (2015)MATHGoogle Scholar
  28. 28.
    Ester, M., Kriegel, H., Xu, X.: Knowledge discovery in large spatial databases: focusing techniques for efficient class identification. In: Proceedings of 4th International Symposium on Large Spatial Databases, pp. 67–82, (1995)Google Scholar
  29. 29.
    Hinneburg, A., Keim, D.: An efficient approach to clustering large multimedia databases with noise. In: Proceedings of 4th International Conference on Knowledge Discovery and Data Mining, pp. 58–65, (1998)Google Scholar
  30. 30.
    Lin, C., Cheng, J., Wu, C.: Mobile location estimation using density-based clustering techniques for NLoS environments. Clust. Comput. 10(1), 3–16 (2007)CrossRefGoogle Scholar
  31. 31.
    Ko, Y., Kim, K., Seo, J.: Topic keyword identification for text summarization using lexical clustering. IEICE Trans. Inform. Syst. 86(9), 1695–1701 (2003)Google Scholar
  32. 32.
    Li, Y., Luo, C., Chung, S.: A parallel text document clustering algorithm based on neighbors. Clust. Comput. 18(2), 933–948 (2015)CrossRefGoogle Scholar
  33. 33.
    Park, K., Lim, H.: Acquiring lexical knowledge using raw corpora and unsupervised clustering method. Clust. Comput. 17(3), 901–910 (2014)CrossRefGoogle Scholar
  34. 34.
    Lee, D., Rim, H.: Probabilistic modeling of Korean morphology. IEEE Trans. Audio Speech Lang. Process. 17(5), 945–955 (2009)CrossRefGoogle Scholar
  35. 35.
    van der Maaten, L.: Accelerating t-SNE using tree-based algorithms. J. Mach. Learn. Res. 15, 3221–3245 (2014)MathSciNetMATHGoogle Scholar
  36. 36.
    Kim, D., Lee, Y., Zhang, J., Rim, H.: Lexical feature embedding for classifying dialogue acts on Korean conversations., In: Proceedings of 42th Winter Conference on Korean Institute of Information Scientists and Engineers, pp. 575–577, (2015)Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Jungsun Jang
    • 1
  • Yeonsoo Lee
    • 1
  • Seolhwa Lee
    • 2
  • Dongwon Shin
    • 2
  • Dongjun Kim
    • 2
  • Haechang Rim
    • 2
  1. 1.AI CenterNCSOFTSeongnam-siKorea
  2. 2.Department of Computer Science and EngineeringKorea UniversitySeoulKorea

Personalised recommendations