Result Diversification Based on Query-Specific Cluster Ranking (Abstract)

Result diversification is a retrieval strategy for dealing with ambiguous or multi-faceted queries by providing documents that cover as many potential facets of the query as possible. We propose a result diversification framework based on query-specific clustering and cluster ranking, in which diversification is restricted to documents belonging to a set of clusters that potentially contain a high percentage of relevant documents. Empirical results on the TREC 2009 Web track test collection show that the proposed framework improves the performance of several existing diversification methods, including MMR, IA-select, and FM-LDA. The framework also gives rise to a simple yet effective cluster-based approach to result diversification that selects documents from different clusters to be included in a ranked list in a round robin fashion.