Advertisement

Similarity Measures for Short Segments of Text

  • Donald Metzler
  • Susan Dumais
  • Christopher Meek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4425)

Abstract

Measuring the similarity between documents and queries has been extensively studied in information retrieval. However, there are a growing number of tasks that require computing the similarity between two very short segments of text. These tasks include query reformulation, sponsored search, and image retrieval. Standard text similarity measures perform poorly on such tasks because of data sparseness and the lack of context. In this work, we study this problem from an information retrieval perspective, focusing on text representations and similarity measures. We examine a range of similarity measures, including purely lexical measures, stemming, and language modeling-based measures. We formally evaluate and analyze the methods on a query-query similarity task using 363,822 queries from a web search log. Our analysis provides insights into the strengths and weaknesses of each method, including important tradeoffs between effectiveness and efficiency.

Keywords

Similarity Measure Short Segment Query Expansion Excellent Match Expanded Representation 
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.
    Berger, A., Lafferty, J.: Information retrieval as statistical translation. In: Proceedings of SIGIR ’99, pp. 222–229 (1999)Google Scholar
  2. 2.
    Cucerzan, S., Brill, E.: Extracting semantically related queries by exploiting user session information. Technical Report, Microsoft Research (2005)Google Scholar
  3. 3.
    Deerwester, S., et al.: Indexing by latent semantic analysis. JASIST 41(6), 391–407 (1990)CrossRefGoogle Scholar
  4. 4.
    Jones, R.: Generating query substitutions. In: Proceedings of WWW 2006, pp. 387-396 (2006)Google Scholar
  5. 5.
    Krovetz, R.: Viewing morphology as an inference process. In: Proceedings of SIGIR ’93, pp. 191–202 (1993)Google Scholar
  6. 6.
    Lavrenko, V., Croft, W.B.: Relevance based language models. In: Proceedings of SIGIR ‘01, pp. 120-127 (2001)Google Scholar
  7. 7.
    Metzler, D., et al.: Similarity measures for tracking information flow. In: Proceedings of CIKM ‘05, pp. 517-524 (2005)Google Scholar
  8. 8.
    Murdock, V., Croft, W.B.: A Translation Model for Sentence Retrieval. In: Proceedings of HLT/EMNLP ‘05, pp. 684-691 (2005)Google Scholar
  9. 9.
    Porter, M.F.: An algorithm for suffix stripping. Program 14(3), 130–137 (1980)Google Scholar
  10. 10.
    Rocchio, J.J.: Relevance Feedback in Information Retrieval, pp. 313–323. Prentice-Hall, Englewood Cliffs (1971)Google Scholar
  11. 11.
    Sahami, M., Heilman, T.: A web-based kernel function for measuring the similarity of short text snippets. In: Proceedings of WWW 2006, pp. 377-386 (2006)Google Scholar
  12. 12.
    Strohman, T., et al.: Indri: A language model-based search engine for complex queries. In: Proceedings of the International Conference on Intelligence Analysis (2005)Google Scholar
  13. 13.
    Zhai, C., Lafferty, J.: A study of smoothing methods for language models applied to ad hoc information retrieval. In: Proceedings of SIGIR ‘01, pp. 334-342 (2001)Google Scholar
  14. 14.
    Zhai, C., Lafferty, J.: Model-based feedback in the language modeling approach to information retrieval. In: Proceedings of CIKM ‘01, pp. 403-410 (2001)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Donald Metzler
    • 1
  • Susan Dumais
    • 2
  • Christopher Meek
    • 2
  1. 1.University of Massachusetts, Amherst, MA 
  2. 2.Microsoft Research, Redmond, WA 

Personalised recommendations