Dynamic Facet Selection by Maximizing Graded Relevance

Abstract

Dynamic faceted search (DFS) allows users to narrow down search results through facets, where the facets-documents mapping is determined at runtime based on the context of user query instead of pre-indexing the facets statically. In this paper, we propose a new unsupervised approach for dynamic facet generation, namely optimistic facets, which attempts to generate the best possible subset of facets, hence maximizing expected Discounted Cumulative Gain (DCG), a measure of ranking quality that uses a graded relevance scale. Additionally, we are open sourcing the code for new evaluation dataset generation. Through empirical results on two datasets, we show that the proposed DFS approach considerably improves the document ranking in the search results.