Advertisement

Easing Erroneous Translations in Cross-Language Image Retrieval Using Word Associations

  • Masashi Inoue
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4022)

Abstract

When short queries and short image annotations are used in text-based cross-language image retrieval, small changes in word usage due to translation errors may decrease the retrieval performance because of an increase in lexical mismatches. In the ImageCLEF2005 ad-hoc task, we investigated the use of learned word association models that represent how pairs of words are related to absorb such mismatches. We compared a precision-oriented simple word-matching retrieval model and a recall-oriented word association retrieval model. We also investigated combinations of these by introducing a new ranking function that generated comparable output values from both models. Experimental results on English and German topics were discouraging, as the use of word association models degraded the performance. On the other hand, word association models helped retrieval for Japanese topics whose translation quality was low.

Keywords

Machine Translation Ranking Function Retrieval Model Word Association Japanese Topic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kraaij, W., de Jong, F.: Transitive CLIR Models. In: RIAO, Vaucluse, France, pp. 69–81 (2004)Google Scholar
  2. 2.
    Inoue, M., Ueda, N.: Retrieving Lightly Annotated Images Using Image Similarities. In: SAC 2005: Proceedings of the 2005 ACM symposium on Applied computing, NY, USA, pp. 1031–1037 (2005)Google Scholar
  3. 3.
    Clough, P., Müller, H., Deselaers, T., Grubinger, M., Lehmann, T.M., Jensen, J., Hersh, W.: The CLEF 2005 Cross–Language Image Retrieval Track. In: Peters, C., Gey, F.C., Gonzalo, J., Müller, H., Jones, G.J.F., Kluck, M., Magnini, B., de Rijke, M., Giampiccolo, D. (eds.) CLEF 2005. LNCS, vol. 4022, pp. 535–557. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Clough, P., Müller, H., Sanderson, M.: The CLEF Cross Language Image Retrieval Track (ImageCLEF) 2004. In: ImageCLEF2004 Working Note (2004)Google Scholar
  5. 5.
    Inoue, M.: Recovering Translation Errors in Cross Language Image Retrieval by Word Association Models. In: ImageCLEF2005 Working Note (2005)Google Scholar
  6. 6.
    Clough, P.: Caption vs. Query Translation for Cross-language Image Retrieval. In: ImageCLEF2004 Working Note (2004)Google Scholar
  7. 7.
    Hiemstra, D., Kraaij, W., Pohlmann, R., Westerveld, T.: Translation Resources, Merging Strategies, and Relevance Feedback for Cross-Language Information Retrieval. In: Peters, C. (ed.) CLEF 2000. LNCS, vol. 2069, pp. 102–115. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Xiang Sean Zhou, T.S.H.: Unifying Keywords and Visual Contents in Image Retrieval. IEEE Multimedia 9, 23–33 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Masashi Inoue
    • 1
  1. 1.National Institute of InformaticsTokyoJapan

Personalised recommendations