Unsupervised query segmentation using click data: preliminary results

J. Kiseleva, Q. Guo, D. Billsus, W. Chai

    Research output: Contribution to conferencePoster

    6 Citations (Scopus)
    1 Downloads (Pure)


    We describe preliminary results of experiments with an unsupervised framework for query segmentation, transforming keyword queries into structured queries. The resulting queries can be used to more accurately search product databases, and potentially improve result presentation and query suggestion. The key to developing an accurate and scalable system for this task is to train a query segmentation or attribute detection system over labeled data, which can be acquired automatically from query and click-through logs. The main contribution of our work is a new method to automatically acquire such training data - resulting in significantly higher segmentation performance, compared to previously reported methods.
    Original languageEnglish
    Publication statusPublished - 2010

    Bibliographical note

    Proceedings of the 19th International Conference on World Wide Web (WWW'10, Raleigh NC, USA, April 26-30, 2010)


    Dive into the research topics of 'Unsupervised query segmentation using click data: preliminary results'. Together they form a unique fingerprint.

    Cite this