ReFER: Effective Relevance Feedback for Entity Ranking

Abstract

Abstract. Web search increasingly deals with structured data about people, places and things, their attributes and relationships. In such an environment an important sub-problem is matching a user's unstructured free-text query to a set of relevant entities. For example, a user might request 'Olympic host cities'. The most challenging general problem is to find relevant entities, of the correct type and characteristics, based on a free-text query that need not conform to any single ontology or category structure. This paper presents an entity ranking relevance feedback model, based on example entities specified by the user or on pseudo feedback. It employs the Wikipedia category structure, but augments that structure with 'smooth categories' to deal with the sparseness of the raw category information. Our experiments show the effectiveness of the proposed method, whether applied as a pseudo relevance feedback method or interactively with the user in the loop.

An exploration of ranking models and feedback method for related entity finding

“…Balog et al (2010), Balog et al (2011) focused on expanding query term model and category model directly from the documents associated with feedback entities. Iofciu, Demartini, Craswell, and de Vries (2011) utilized the Wikipedia category graph structure to estimate the entity ranking weight which is interpolated with the initial ranking as the final one. However, their models heavily rely on the structure of Wikipedia (e.g.…”

iQbees: Interactive Query-by-example Entity Search in Semantic Knowledge Graphs

“…Only very recently, Su et al [16] proposed exploiting relevance feedback for improving results of searching a knowledge graph, but not for entity search. For entity ranking using text or semi-structured information, relevance feedback has been more popular [17].…”