Exploiting MDS Projections for Cross-language IR

ABSTRACT

In this paper, we describe some preliminary work on using monolingual projections of document collections for performing cross-language information retrieval tasks. The proposed methodology uses multidimensional scaling for projecting the vector-space representations of a given multilingual document collection into spaces of lower dimensionality. An independent projection is computed for each different language, and the structural similarities of the resulting projections are exploited for information retrieval tasks.

REFERENCES

• 1: M. F. Cox and M. A. A. Cox. Multidimensional Scaling. Chapman & Hall, London, UK, 2001.
• 2: S. T. Dumais, T. K. Landauer, and M. L. Littman. Automatic cross-linguistic information retrieval using latent semantic indexing. In SIGIR96 Workshop On Cross-Linguistic Information Retrieval, 1996.
• 3: Kazuaki Kishida, Technical issues of cross-language information retrieval: a review, Information Processing and Management: an International Journal, v.41 n.3, p.433-455, May 2005 [doi>10.1016/j.ipm.2004.06.007]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Clustering

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Search process; Retrieval models

General Terms:
Algorithms, Experimentation

Keywords:
IR, cross-language, multidimensional scaling