| Title: | Page Hunt: Improving Search Engines Using Human Computation Games |
| Date: |
November 2, 2009 (Monday)
|
| Time: |
10:30 a.m. - 11:30 a.m.
|
| Venue: |
Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong, Shatin, N.T. |
| Speaker: |
Dr. Raman Chandrasekar
Researcher Microsoft Research |
Work on evaluating and improving the relevance of web search engines typically use human relevance judgments or clickthrough data. Both these methods look at the problem of learning the mapping from queries to web pages. In this talk, we identify some issues with this approach, and suggest an alternative approach, namely, learning a mapping from web pages to queries. In particular, we use human computation games to elicit data from players about web pages that can be used to improve search. We describe three human computation games that we developed, with a focus on Page Hunt (available at http://pagehunt.msrlivelabs.com ), a single-player game. We describe experiments we conducted with several hundred game players, highlight some interesting aspects of the data obtained and define a 'findability' metric. We also show how we automatically extract query alterations using techniques from bitext matching, for use in query refinement. The data that we elicit from players has several other applications including providing metadata for pages and identifying ranking issues.
[Forthcoming paper at CIKM 2009; Joint work with Hao Ma of CUHK, Chris Quirk and Abhishek Gupta]
BIOGRAPHY:
Raman Chandrasekar is a Researcher in the Text Mining, Search and Navigation (TMSN) group in Microsoft Research, Redmond. His work at Microsoft has focused on topics at the intersection of information retrieval and natural language processing. His current interests include aspects of targeted/topical search, human computation and search & advertising relevance. More info is available at http://research.microsoft.com/en-us/people/ramanc/
Enquiries: Miss Temmy So at tel 2609 8444
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar