Effects of Aligned Corpus Quality and Size in Corpus-Based CLIR

  • Tuomas Talvensaari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4956)

Abstract

Aligned corpora are often-used resources in CLIR systems. The three qualities of translation corpora that most dramatically affect the performance of a corpus-based CLIR system are: (1) topical nearness to the translated queries, (2) the quality of the alignments, and (3) the size of the corpus. In this paper, the effects of these factors are studied and evaluated. Topics of two different domains (news and genomics) are translated with corpora of varying alignment quality, ranging from a clean parallel corpus to noisier comparable corpora. Also, the sizes of the corpora are varied. The results show that of the three qualities, topical nearness is the most crucial factor, outweighing both other factors. This indicates that noisy comparable corpora should be used as complimentary resources, when parallel corpora are not available for the domain in question.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Oard, D.W., Diekema, A.R.: Cross-Language Information Retrieval. Annual Review of Information Science and Technology (ARIST) 33, 223–256 (1998)Google Scholar
  2. 2.
    Pirkola, A., Hedlund, T., Keskustalo, H., Järvelin, K.: Dictionary-Based Cross-Language Information Retrieval: Problems, Methods, and Research Findings. Inf. Retr. 4, 209–230 (2001)MATHCrossRefGoogle Scholar
  3. 3.
    Sheridan, P., Ballerini, J.P.: Experiments in Multilingual Information Retrieval Using the SPIDER System. In: SIGIR 1996: Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 58–65. ACM Press, New York (1996)CrossRefGoogle Scholar
  4. 4.
    Franz, M., McCarley, J.S., Ward, T., Zhu, W.J.: Quantifying the Utility of Parallel Corpora. In: SIGIR 2001: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 398–399. ACM Press, New York (2001)CrossRefGoogle Scholar
  5. 5.
    Zhu, J., Wang, H.: The Effect of Translation Quality in MT-Based Cross-Language Information Retrieval. In: ACL 2006: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the ACL, pp. 593–600. Association for Computational Linguistics, Morristown, NJ (2006)CrossRefGoogle Scholar
  6. 6.
    Xu, J., Weischedel, R.: Empirical Studies on the Impact of Lexical Resources on CLIR Performance. Inf. Process. Manage. 41, 475–487 (2005)MATHCrossRefGoogle Scholar
  7. 7.
    Peters, C.: What Happened in CLEF 2006. In: Peters, C., Clough, P., Gey, F.C., Karlgren, J., Magnini, B., Oard, D.W., de Rijke, M., Stempfhuber, M. (eds.) CLEF 2006. LNCS, vol. 4730, pp. 1–10. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufiş, D., Varga, D.: The JRC-Acquis: A Multilingual Aligned Parallel Corpus with 20+ Languages. In: LREC 2006:Proceedings of the 5th International Conference on Language Resources and Evaluation, pp. 2142–2147. European Language Resources Association, Paris (2006)Google Scholar
  9. 9.
    Talvensaari, T., Laurikkala, J., Järvelin, K., Juhola, M., Keskustalo, H.: Creating and Exploiting a Comparable Corpus in Cross-language Information Retrieval. ACM Trans. Inf. Syst. 25, 4 (2007)CrossRefGoogle Scholar
  10. 10.
    Allan, J., Callan, J.P., Croft, W.B., Ballesteros, L., Broglio, J., Xu, J., Shu, H.: Inquery at TREC-5. In: TREC-5: The Fifth Text Retrieval Conference, pp. 119–132. National Institute of Standards and Technology (1996)Google Scholar
  11. 11.
    Talvensaari, T., Järvelin, K., Pirkola, A., Juhola, M., Laurikkala, J.: Focused Web Crawling in Acquisition of Comparable Corpora. Information Retrieval (submitted, 2007)Google Scholar
  12. 12.
    Chakrabarti, S., van den Berg, M., Dom, B.: Focused Crawling: a New Approach to Topic-specific Web Resource Discovery. In: WWW 1999: Proceeding of the Eighth International Conference on World Wide Web, pp. 1623–1640. Elsevier North-Holland, Inc (1999)Google Scholar
  13. 13.
    Singhal, A., Buckley, C., Mitra, M.: Pivoted Document Length Normalization. In: SIGIR 1996: Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 21–29. ACM Press, New York (1996)CrossRefGoogle Scholar
  14. 14.
    Hersh, W.R.: Report on the TREC 2004 Genomics Track. SIGIR Forum 39, 21–24 (2005)CrossRefGoogle Scholar
  15. 15.
    Keskustalo, H., Hedlund, T., Airio, E.: Utaclir: General Query Translation Framework for Several Language Pairs. In: SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 448–448. ACM Press, New York (2002)CrossRefGoogle Scholar
  16. 16.
    McNamee, P., Mayfield, J.: Comparing Cross-language Query Expansion Techniques by Degrading Translation Resources. In: SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 159–166. ACM Press, New York (2002)CrossRefGoogle Scholar
  17. 17.
    Pirkola, A.: The Effects of Query Structure and Dictionary Setups in Dictionary-based Cross-language Information Retrieval. In: SIGIR 1998: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 55–63. ACM Press, New York (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Tuomas Talvensaari
    • 1
  1. 1.Department of Computer SciencesUniversity of TampereFinland

Personalised recommendations