Enhancing Software Search with Semantic Information from Wikipedia

Conference paper
Part of the Springer Proceedings in Complexity book series (SPCOM)

Abstract

Software is becoming ubiquitous, from desktop computers to smart phones, and has created significant impact on the quality of our everyday life. Sharing and reusing high-quality software can save tremendous amount of time and efforts that otherwise would need to be reinvented. The challenge is how to efficiently search through a potentially huge database of software and return the most relevant results. In this paper, we present a prototype of semantic software search engine that exploits the semantic information from Wikipedia, one of the largest online knowledge repositories as the result of collaborative intelligence. We propose a technique to replace the original concept space by an extended concept space extracted from Wikipedia to incorporate commonsense knowledge into software search. Experimental results show that this strategy can achieve better performance over traditional software search based on the original concept space.

Notes

Acknowledgments

This work was supported by the National Natural Science Foundation of China (No. 60905030). The authors are also grateful to Prof. Juanzi Li for her kind help.

References

  1. 1.
    Waitelonis, J., Sack, H., Hercher, J., Kramer, Z.: Semantically enabled exploratory video search. In: 3rd International Semantic Search Workshop, Article No. 8 (2010)Google Scholar
  2. 2.
    Gabrilovich, E., Markovitch, S.: Computing semantic relatedness using wikipedia-based explicit semantic analysis. In: 20th International Joint Conference on Artificial Intelligence, pp. 1606–1611 (2007)Google Scholar
  3. 3.
    Coursey, K., Mihalcea, R.: Topic identification using wikipedia graph centrality. In: 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pp. 117–120 (2009)Google Scholar
  4. 4.
    Banerjee, S., Ramanathan, K., Gupta, A.: Clustering short texts using wikipedia. In: 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 787–788 (2007)Google Scholar
  5. 5.
    Yang, J., Han, J., Oh, I., Kwak, M.: Using wikipedia technology for topic maps design. In: 45th Annual Southeast Regional Conference, pp. 106–110 (2007)Google Scholar
  6. 6.
    Medelyan, O., Witten, I.H., Milne, D.: Topic indexing with wikipedia. In: AAAI Workshop on Wikipedia and Artificial Intelligence: An Evolving Synergy, pp. 19–24 (2008)Google Scholar
  7. 7.
    Milne, D.: Computing semantic relatedness using wikipedia link structure. In: New Zealand Computer Science Research Student Conference (2007)Google Scholar
  8. 8.
    Tumer, D., Shah, M.A., Bitirim, Y.: An empirical evaluation on semantic search performance of keyword-based and semantic search engines: Google, Yahoo, Msn and Hakia. In: Fourth International Conference on Internet Monitoring and Protection, pp. 51–55 (2009)Google Scholar
  9. 9.
    Völkel, M., Krötzsch, M., Vrandecic, D., Haller, H., Studer, R.: Semantic wikipedia. In: 15th International Conference on World Wide Web, pp. 585–594 (2006)Google Scholar
  10. 10.
    Kaptein, R., Serdyukov, P., De Vries, A., Kamps, J.: Entity ranking using wikipedia as a pivot. In: 19th ACM International Conference on Information and Knowledge Management, pp. 69–78 (2010)Google Scholar
  11. 11.
    Chernov, S., Iofciu, T., Nejdl, W., Zhou, X.: Extracting semantic relationships between wikipedia categories. In: First Workshop on Semantic Wikis – From Wiki to Semantics (2006)Google Scholar
  12. 12.
    Strube, M., Ponzetto, S.P.: WikiRelate! Computing semantic relatedness using wikipedia. In: 21st National Conference on Artificial Intelligence, pp. 1419–1424 (2006)Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Intelligent Computing Lab, Division of Informatics, Graduate School at ShenzhenTsinghua UniversityShenzhenPeople’s Republic of China

Personalised recommendations