A Feature-Enriched Method for User Intent Classification by Leveraging Semantic Tag Expansion

  • Wenxiu Xie
  • Dongfa GaoEmail author
  • Ruoyao Ding
  • Tianyong HaoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)


User intent identification and classification has become a vital topic of query understanding in human-computer dialogue applications. The identification of users’ intent is especially crucial for assisting system to understand users’ queries so as to classify the queries accurately to improve users’ satisfaction. Since the posted queries are usually short and lack of context, conventional methods heavily relying on query n-grams or other common features are not sufficient enough. This paper proposes a compact yet effective user intention classification method named as ST-UIC based on a constructed semantic tag repository. The method proposes to use a combination of four kinds of features including characters, non-key-noun part-of-speech tags, target words, and semantic tags. The experiments are based on a widely applied dataset provided by the First Evaluation of Chinese Human-Computer Dialogue Technology. The result shows that the method achieved a F1 score of 0.945, exceeding a list of baseline methods and demonstrating its effectiveness in user intent classification.


User intent Classification Target Words Semantic Tag 



This work was supported by National Natural Science Foundation of China (No.61772146) and Innovative School Project in Higher Education of Guangdong Province (No.YQ2015062). Guangzhou Science Technology and Innovation Commission (No. 201803010063).


  1. 1.
    Zhang, W.-N., Chen, Z., Che, W., Hu, G., Liu, T.: The First Evaluation of Chinese Human-Computer Dialogue Technology. arXiv preprint arXiv:1709.10217 (2017)
  2. 2.
    Zue, V., Seneff, S.: Spoken dialogue systems. Synth. Lect. Hum. Lang. Technol. 2, 1–151 (2009)Google Scholar
  3. 3.
    Tur, G., Deng, L., Hakkani-Tür, D., He, X.: Towards deeper understanding: deep convex networks for semantic utterance classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5045–5048 (2012)Google Scholar
  4. 4.
    Zhang, J., Yang, T.Z., Hazen, T.J.: Large-scale word representation features for improved spoken language understanding. In: International Conference on Acoustics, Speech and Signal Processing, pp. 5306–5310 (2015)Google Scholar
  5. 5.
    Liu, J., Pasupat, P., Wang, Y., Cyphers, S., Glass, J.: Query understanding enhanced by hierarchical parsing structures. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 72–77 (2013)Google Scholar
  6. 6.
    Liu, B., Lane, I.: Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding. arXiv preprint arXiv:1711.11310. pp. 1–6 (2017)
  7. 7.
    Xu, P., Sarikaya, R.: Contextual domain classification in spoken language understanding systems using recurrent neural network. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3–7 (2014)Google Scholar
  8. 8.
    Ashkan, A., Clarke, C.L.A., Agichtein, E., Guo, Q.: Classifying and characterizing query intent. In: Boughanem, M., Berrut, C., Mothe, J., Soule-Dupuy, C. (eds.) ECIR 2009. LNCS, vol. 5478, pp. 578–586. Springer, Heidelberg (2009). Scholar
  9. 9.
    Hu, J., Wang, G., Lochovsky, F., Sun, J., Chen, Z.: Understanding user’s query intent with Wikipedia. In: International Conference on World Wide Web, pp. 471–480. ACM (2009)Google Scholar
  10. 10.
    Park, K., Jee, H., Lee, T., Jung, S., Lim, H.: Automatic extraction of user’s search intention from web search logs. Multimed. Tools Appl. 61, 145–162 (2012)CrossRefGoogle Scholar
  11. 11.
    Jansen, B.J., Booth, D.L., Spink, A.: Determining the user intent of web search engine queries. In: International Conference on World Wide Web, pp. 1149–1150. ACM (2007)Google Scholar
  12. 12.
    Zhang, S., Wang, B.: A survey of web search query intention classification. J. Chin. Inf. Process. 22(4), 75–82 (2008)Google Scholar
  13. 13.
    Yu, H., Liu, Y., Zhang, M., Ru, L., Ma, S.: Research in search engine user behavior based on log analysis. J. Chin. Inf. Process. 21, 109–114 (2007)Google Scholar
  14. 14.
    De Mori, R., Béchet, F., Hakkani-Tür, D., McTear, M., Riccardi, G., Tur, G.: Spoken language understanding: a survey. In: Automatic Speech Recognition and Understanding Workshop, pp. 365–376 (2007)Google Scholar
  15. 15.
    Hao, T., Xie, W., Wu, Q., Weng, H., Qu, Y.: Leveraging question target word features through semantic relation expansion for answer type classification. Knowl. Based Syst. 133, 43–52 (2017)CrossRefGoogle Scholar
  16. 16.
    Hao, T., Xie, W., Xu, F.: A wordnet expansion-based approach for question targets identification and classification. In: Sun, M., Liu, Z., Zhang, M., Liu, Y. (eds.) CCL 2015. LNCS (LNAI), vol. 9427, pp. 333–344. Springer, Cham (2015). Scholar
  17. 17.
    Gorin, A., Riccardi, G., Wright, J.: How may I help you? Speech Commun. 23, 113–127 (1997)CrossRefGoogle Scholar
  18. 18.
    Gupta, N., Tur, G., Hakkani-Tur, D., Bangalore, S., Riccardi, G., Gilbert, M.: The AT&T spoken language understanding system. IEEE Trans. Audio Speech Lang. Process. 14(1), 213–222 (2006)CrossRefGoogle Scholar
  19. 19.
    Hakkani-Tür, D., Heck, L., Tur, G.: Exploiting query click logs for utterance domain detection in spoken language understanding. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5636–5639 (2011)Google Scholar
  20. 20.
    Celikyilmaz, A., Hakkani-Tür, D., Tur, G.: Leveraging web query logs to learn user intent via bayesian discrete latent variable model. In: International Conference on Machine Learning (2011)Google Scholar
  21. 21.
    Hernández, I., Gupta, D., Rosso, P., Rocha, M.: A simple model for classifying web queries by user intent. In: Spanish Conference Information Retrieval, pp. 235–240 (2012)Google Scholar
  22. 22.
    Ganti, V., König, A.C., Li, X.: Precomputing search features for fast and accurate query classification. In: ACM International Conference on Web Search and Data Mining, pp. 61–70 (2010)Google Scholar
  23. 23.
    Deng, L., Tur, G., He, X., Hakkani-Tur, D.: Use of kernel deep convex networks and end-to-end learning for spoken language understanding. In: IEEE Workshop on Spoken Language Technology, pp. 210–215 (2012)Google Scholar
  24. 24.
    Shi, Y., Yao, K., Chen, H., Pan, Y.-C.Y., Hwang, M.-Y., Peng, B.: Contextual spoken language understanding using recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5271–5275 (2015)Google Scholar
  25. 25.
    Bengio, Y.: Deep learning of representations: looking forward. In: Dediu, A.-H., Martín-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS (LNAI), vol. 7978, pp. 1–37. Springer, Heidelberg (2013). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Information Science and TechnologyGuangdong University of Foreign StudiesGuangzhouChina
  2. 2.School of Computer ScienceSouth China Normal UniversityGuangzhouChina

Personalised recommendations