Query Disambiguation Based on Novelty and Similarity User's Feedback
Gloria Bordogna, Alessandro Siro Campi, Stefania Ronchi, Giuseppe Psaila · 2009
In this paper we propose a query disambiguation mechanism focalizing the query context by applying clustering to the results of a Web-search. The clusters are ranked to reflect a balance of their contents’ novelty and overall similarity with respect to the original query, and, from each of them, a disambiguated query is generated so as to potentially retrieve new documents focalized on the cluster contents.