Advertisement

A Comparison of Approaches for Measuring Cross-Lingual Similarity of Wikipedia Articles

  • Alberto Barrón-Cedeño
  • Monica Lestari Paramita
  • Paul Clough
  • Paolo Rosso
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8416)

Abstract

Wikipedia has been used as a source of comparable texts for a range of tasks, such as Statistical Machine Translation and Cross-Language Information Retrieval. Articles written in different languages on the same topic are often connected through inter-language-links. However, the extent to which these articles are similar is highly variable and this may impact on the use of Wikipedia as a comparable resource. In this paper we compare various language-independent methods for measuring cross-lingual similarity: character n-grams, cognateness, word count ratio, and an approach based on outlinks. These approaches are compared against a baseline utilising MT resources. Measures are also compared to human judgements of similarity using a manually created resource containing 700 pairs of Wikipedia articles (in 7 language pairs). Results indicate that a combination of language-independent models (char-n-grams, outlinks and word-count ratio) is highly effective for identifying cross-lingual similarity and performs comparably to language-dependent models (translation and monolingual analysis).

Keywords

Wikipedia Cross-Lingual Similarity 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Adafre, S., de Rijke, M.: Finding Similar Sentences across Multiple Languages in Wikipedia. In: Proc. of the 11th Conf. of the European Chapter of the Association for Computational Linguistics, pp. 62–69 (2006)Google Scholar
  2. 2.
    Dumais, S., Letsche, T., Littman, M., Landauer, T.: Automatic Cross-Language Retrieval Using Latent Semantic Indexing. In: AAAI 1997 Spring Symposium Series: Cross-Language Text and Speech Retrieval, Stanford University, pp. 24–26 (1997)Google Scholar
  3. 3.
    Filatova, E.: Directions for exploiting asymmetries in multilingual Wikipedia. In: Proc. of the Third Intl. Workshop on Cross Lingual Information Access: Addressing the Information Need of Multilingual Societies, Boulder, CO (2009)Google Scholar
  4. 4.
    Levow, G.A., Oard, D., Resnik, P.: Dictionary-Based Techniques for Cross-Language Information Retrieval. Information Processing and Management: Special Issue on Cross-Language Information Retrieval 41(3), 523–547 (2005)CrossRefGoogle Scholar
  5. 5.
    Mcnamee, P., Mayfield, J.: Character N-Gram Tokenization for European Language Text Retrieval. Information Retrieval 7(1-2), 73–97 (2004)CrossRefGoogle Scholar
  6. 6.
    Mihalcea, R.: Using Wikipedia for Automatic Word Sense Disambiguation. In: Proc. of NAACL 2007. ACL, Rochester (2007)Google Scholar
  7. 7.
    Mohammadi, M., GhasemAghaee, N.: Building Bilingual Parallel Corpora based on Wikipedia. In: Second Intl. Conf. on Computer Engineering and Applications., vol. 2, pp. 264–268 (2010)Google Scholar
  8. 8.
    Munteanu, D., Fraser, A., Marcu, D.: Improved Machine Translation Performace via Parallel Sentence Extraction from Comparable Corpora. In: Proc. of the Human Language Technology and North American Association for Computational Linguistics Conf (HLT/NAACL 2004), Boston, MA (2004)Google Scholar
  9. 9.
    Nguyen, D., Overwijk, A., Hauff, C., Trieschnigg, D.R.B., Hiemstra, D., de Jong, F.: WikiTranslate: Query Translation for Cross-Lingual Information Retrieval Using Only Wikipedia. In: Peters, C., Deselaers, T., Ferro, N., Gonzalo, J., Jones, G.J.F., Kurimo, M., Mandl, T., Peñas, A., Petras, V. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 58–65. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  10. 10.
    Paramita, M.L., Clough, P.D., Aker, A., Gaizauskas, R.: Correlation between Similarity Measures for Inter-Language Linked Wikipedia Articles. In: Calzolari, E.A. (ed.) Proc. of the 8th Intl. Language Resources and Evaluation (LREC 2012), pp. 790–797. ELRA, Istanbul (2012)Google Scholar
  11. 11.
    Potthast, M., Stein, B., Anderka, M.: A Wikipedia-Based Multilingual Retrieval Model. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol. 4956, pp. 522–530. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  12. 12.
    Simard, M., Foster, G.F., Isabelle, P.: Using Cognates to Align Sentences in Bilingual Corpora. In: Proc. of the Fourth Intl. Conf. on Theoretical and Methodological Issues in Machine Translation (1992)Google Scholar
  13. 13.
    Steinberger, R., Pouliquen, B., Hagman, J.: Cross-lingual Document Similarity Calculation Using the Multilingual Thesaurus EUROVOC. In: Gelbukh, A. (ed.) CICLing 2002. LNCS, vol. 2276, pp. 415–424. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  14. 14.
    Toral, A., Muñoz, R.: A proposal to automatically build and maintain gazetteers for Named Entity Recognition using Wikipedia. In: Proc. of the EACL Workshop on New Text 2006. Association for Computational Linguistics, Trento (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Alberto Barrón-Cedeño
    • 1
  • Monica Lestari Paramita
    • 2
  • Paul Clough
    • 2
  • Paolo Rosso
    • 3
  1. 1.Talp Research CenterUniversitat Politècnica de CatalunyaBarcelonaSpain
  2. 2.Information SchoolUniversity of SheffieldSheffieldUK
  3. 3.NLE Lab, PRHLTUniversitat Politècnica de ValènciaValenciaSpain

Personalised recommendations