Click logs provide a highly valuable source of relevance information. Compared to editorial labels, clicks are much cheaper to obtain and always reflect current relevance. Click models have been shown to be very successful for obtaining relevance judgements from the click logs.

The idea is to implement a module capable of logging the click information from Omega and mine relevance judgements from it that would complement the existing letor module in Xapian. Another significant part of the project will include writing clear documentation for the logging and other parts of the project so people can use it to produce relevance judgements easily.


Vivek Pal


  • Amanda Jayanetti