Clustering Web search results into contexts

摘要

It is a common experience while Web searching that one gets to see pages that are not of interest. Partly these are due to a word or words in the search query having different contexts, the user obviously expecting to find pages related to the context of interest. This paper proposes a method for disambiguating contexts in Web search results. It was seen from the tests that the algorithms perform very well even when they have very little information to work with. Thus implementing context disambiguation as a meta-service may be an interesting experiment. Search engines usually provide results in pages of 10 (or more) results. Thus, a meta-service implementation of the disambiguator need process only 2-3 result lists, and thus 20-30 pages, at a given time and can defer the disambiguation of other pages to a time when they are actually required.