Precision-Oriented Query Facet Extraction

Abstract

Faceted search has been used successfully for many vertical applications such as e-commerce and digital libraries. However, it remains challenging to extend faceted search to the open-domain web due to the large and heterogeneous nature of the web. Recent work proposed an alternative solution that extracts facets for queries from their web search results, but neglected the precision-oriented perspective of the task-users are likely to care more about precision of presented facets than recall. We improve query facet extraction performance under a precision-oriented scenario from two perspectives. First, we propose an empirical utility maximization approach to learn a probabilistic model by maximizing the expected performance measure instead of likelihood as used in previous approaches. We show that the empirical utility maximization approach can significantly improve over the previous approach under the precision-oriented scenario. Second, instead of showing facets for all queries, we propose a selective method that predicts the extraction performance for each query and selectively shows facets for some of them. We show the selective method can significantly improve the average performance with fair coverage over the whole query set.

Solution for Information Overload Using Faceted Search–A Review

“…Faceted allows complex filters to be used in several phases to analyze data. When a filter is created, the searcher shows the results, with the preference that more filters are created or the current filters, are modified [175]. Instead of restricting them in a specific direction, the strength of FS lies in the capacity of users to construct their own personal navigation by combining different experiences.…”

Incorporating Hierarchical Domain Information to Disambiguate Very Short Queries

“…Other studies have explored the modeling of concept hierarchies for providing a hierarchical map of words [3,10,11,16]. More recently, much work has been done on search result diversification based on facet extraction [9] as well as incorporating hierarchical domain information [7,18]. Search result diversification is a wellstudied technique that aims to cover multiple facets of ambiguous and faceted queries in the result page, so that the user is able to find documents that are relevant to their actual information need.…”

Evaluating Search Results in Exploratory Search

“…Faceted browsing allows application of dynamic filters in exploring data in several phases. That is, whenever a filter is applied, the results are shown to the user, who has the prerogative to apply additional filters or modify existing ones [32,33]. The power of FSS rests in the ability of users to create their own custom navigation by combining various perceptions rather than constraining them through a definite path.…”