Exploiting Result Consistency to Select Query Expansions for Spoken Content Retrieval

  • Stevan Rudinac
  • Martha Larson
  • Alan Hanjalic
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5993)


We propose a technique that predicts both if and how expansion should be applied to individual queries. The prediction is made on the basis of the topical consistency of the top results of the initial results lists returned by the unexpanded query and several query expansion alternatives. We use the coherence score, known to capture the tightness of topical clustering structure, and also propose two simplified coherence indicators. We test our technique in a spoken content retrieval task, with the intention of helping to control the effects of speech recognition errors. Experiments use 46 semantic-theme-based queries defined by VideoCLEF 2009 over the TRECVid 2007 and 2008 video data sets. Our indicators make the best choice roughly 50% of the time. However, since they predict the right query expansion in critical cases, overall MAP improves. The approach is computationally lightweight and requires no training data.


Speech-transcript-based video retrieval query expansion query performance prediction list coherence source selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yom-Tov, E., Fine, S., Carmel, D., Darlow, A.: Learning to estimate query difficulty. In: SIGIR 2005, pp. 512–519 (2005)Google Scholar
  2. 2.
    Hauff, C., Murdock, V., Yates, R.B.: Improved query difficulty prediction for the web. In: CIKM 2008, pp. 439–448 (2008)Google Scholar
  3. 3.
    Byrne, W., et al.: Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans. SAP 12(4), 420–435 (2004)Google Scholar
  4. 4.
    Huijbregts, M., Ordelman, R., de Jong, F.: Annotation of heterogeneous multimedia content using automatic speech recognition. In: Falcidieno, B., Spagnuolo, M., Avrithis, Y., Kompatsiaris, I., Buitelaar, P. (eds.) SAMT 2007. LNCS, vol. 4816, pp. 78–90. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  5. 5.
    Cronen-Townsend, S., Zhou, Y., Croft, W.B.: Predicting query performance. In: SIGIR 2002, pp. 299–306 (2002)Google Scholar
  6. 6.
    Olsson, J.S., Oard, D.W.: Combining Speech Retrieval Results with Generalized Additive Models. In: ACL 2008: HLT, pp. 461–469 (2008)Google Scholar
  7. 7.
    He, J., Weerkamp, W., Larson, M., de Rijke, M.: An effective coherence measure to determine topical consistency in user-generated content. International Journal on Document Analysis and Recognition 12(3), 185–203 (2009)CrossRefGoogle Scholar
  8. 8.
    Rudinac, S., Larson, M., Hanjalic, A.: Exploiting visual reranking to improve pseudo-relev-ance feedback for spoken-content-based video retrieval. In: WIAMIS 2009, pp. 17–20 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Stevan Rudinac
    • 1
  • Martha Larson
    • 1
  • Alan Hanjalic
    • 1
  1. 1.Multimedia Information Retrieval LabDelft University of TechnologyDelftThe Netherlands

Personalised recommendations