Automatic query taxonomy generation for information retrieval applications

It is crucial for information retrieval systems to learn more about what users search for in order to fulfill the intent of search. This paper introduces a new problem, called query taxonomy generation, which is trying to organize users’ queries into a hierarchical structure of topic classes. Such a query taxonomy provides a basis for the in-depth analysis of users’ queries on a larger scale and can benefit many information retrieval systems. The proposed approach to this problem consists of two computational processes: hierarchical query clustering to generate a query taxonomy from scratch, and query categorization to place new-arrived queries into the taxonomy. The obtained results of preliminary experiment have shown the potential of the proposed approach in generating taxonomies for queries, which may be useful in various Web information retrieval applications.