Entity-based Stochastic Analysis of Search Results for Query Expansion and Results Re-Ranking
Foundation for Research and Technology - Hellas (FORTH) -ICS Heraklion, Crete Greece
Pagination or Media Count:
In this paper we introduce a method for exploiting entities from the emerging Web of Data for enhancing various Information Retrieval IR services. The approach is based on named-entity recognition applied in a set of search results, and on a graph of documents and identified entities that is constructed dynamically and analyzed stochastically using a Random Walk method. The result of this analysisis exploited in two different contexts for automatic query expansion and for re-ranking a set of retrieved results. Evaluation results in the 2015 TREC Clinical Decision Support Track illustrate that query expansion can increase recall by retrieving more relevant hits, while re-ranking can notably improve the ranked list of results by moving relevant but low-ranked hits in higher positions.