HAMSTER: Using Search Clicklogs for Schema and Taxonomy Matching

Just got done with the HAMSTER presentation; here is the paper, and here are my abstract and slides:

We address the problem of unsupervised matching of schema information from a large number of data sources into the schema of a data warehouse. The matching process is the first step of a framework to integrate data feeds from third-party data providers into a structured-search engine’s data warehouse. Our experiments show that traditional schema- based and instance-based schema matching methods fall short. We propose a new technique based on the search engine’s clicklogs. Two schema elements are matched if the distribution of keyword queries that cause click-throughs on their instances are similar. We present experiments on large commercial datasets that show the new technique has much better accuracy than traditional techniques.

I received a few questions after the talk, hence I thought I’d put up a quick FAQ:

Q: Doesn’t the time(period) of the clicklog affect your integration quality?

A: Yes. And we consider this a good thing. This allows trend information to come into the system, e.g. “pokemon” queries will start coming in, and merge “japanese toys” with “children’s collector items”. Unpopular items that are not searched for may not generate a mapping, but then again, this may be ok since the end goal was to integrate searched-for items.

Q: You use clicklogs. I am a little old company/website owner X. Since my company’s name doesn’t start with G, M or Y, I don’t have clicklogs. How do I use your method?

A: You already have clicklogs. Let’s say you are trying to merge your company/website X’s data with company Y’s data. Since both you (X) and Y have websites, you both run HTTP servers, which have the facility to log requests. Look through your HTTP server referral logs for strings like:
URL: http://x.com
REFERRER: http://www.google.com/?q=$search_string$

This is your clicklog. The url http://x.com has the query $search_string$. You can grep both websites to create clicklogs, which can then be used to integration.

Q: My website is not very popular and I don’t have that many clicks from search engines. What do I do?

A: Yup, this is a very real case. Specifically, you might have a lot of queries for some of your items, but not for others. This can be balanced out. See the section in our paper about Surrogate Clicklogs. Basically you can use a popular website’s clicklog as a “surrogate” log for your database. From the paper:

…we propose a method by which we identify surrogate clicklogs for any data source without significant web presence. For each candidate entity in the feed that does not have a significant presence in the clicklogs (i.e. clicklog volume is less than a threshold), we look for an entity in our collection of feeds that is most similar to the candidate, and use its clicklog data to generate a query distribution for the candidate object.

Q: I am an academic and do not have access to a public clicklog, or a public website to do get clicklogs from. How do I use this technique?

A: Participate in the Lemur project and get your friends to participate too.

|

About the author:

Arnab Nandi is an Assistant Professor in the Department of Computer Science and Engineering at The Ohio State University. You can read more about him here.


August 2002 : 9 posts September 2002 : 16 posts October 2002 : 7 posts November 2002 : 21 posts December 2002 : 25 posts January 2003 : 8 posts February 2003 : 11 posts March 2003 : 7 posts April 2003 : 21 posts May 2003 : 14 posts June 2003 : 15 posts July 2003 : 4 posts August 2003 : 16 posts September 2003 : 25 posts October 2003 : 15 posts November 2003 : 24 posts December 2003 : 17 posts January 2004 : 6 posts February 2004 : 8 posts March 2004 : 6 posts April 2004 : 5 posts May 2004 : 29 posts June 2004 : 3 posts July 2004 : 17 posts August 2004 : 19 posts September 2004 : 3 posts October 2004 : 4 posts December 2004 : 1 posts February 2005 : 15 posts March 2005 : 18 posts April 2005 : 8 posts May 2005 : 27 posts June 2005 : 73 posts July 2005 : 45 posts August 2005 : 13 posts September 2005 : 3 posts October 2005 : 9 posts November 2005 : 20 posts December 2005 : 6 posts January 2006 : 25 posts February 2006 : 24 posts March 2006 : 37 posts April 2006 : 35 posts May 2006 : 7 posts June 2006 : 22 posts July 2006 : 20 posts August 2006 : 27 posts September 2006 : 15 posts October 2006 : 6 posts November 2006 : 19 posts December 2006 : 4 posts January 2007 : 4 posts February 2007 : 1 posts March 2007 : 3 posts May 2007 : 5 posts June 2007 : 2 posts July 2007 : 1 posts August 2007 : 13 posts September 2007 : 2 posts October 2007 : 21 posts November 2007 : 7 posts December 2007 : 9 posts January 2008 : 4 posts February 2008 : 14 posts March 2008 : 14 posts April 2008 : 11 posts May 2008 : 12 posts June 2008 : 12 posts July 2008 : 5 posts August 2008 : 10 posts September 2008 : 11 posts October 2008 : 10 posts November 2008 : 8 posts December 2008 : 4 posts January 2009 : 6 posts February 2009 : 13 posts March 2009 : 7 posts April 2009 : 7 posts May 2009 : 2 posts June 2009 : 3 posts July 2009 : 4 posts August 2009 : 4 posts September 2009 : 6 posts October 2009 : 4 posts November 2009 : 7 posts December 2009 : 10 posts January 2010 : 3 posts February 2010 : 2 posts April 2010 : 5 posts May 2010 : 1 posts July 2010 : 4 posts August 2010 : 3 posts September 2010 : 4 posts October 2010 : 1 posts November 2010 : 2 posts December 2010 : 3 posts June 2011 : 1 posts August 2011 : 1 posts November 2011 : 1 posts December 2011 : 1 posts February 2012 : 1 posts May 2012 : 2 posts December 2012 : 1 posts June 2013 : 1 posts August 2013 : 1 posts October 2013 : 2 posts