Constructing Web search queries from the user's information need expressed in a natural language

This paper focuses on improving the quality of information retrieval on the Web through the use of long queries. Long queries allow use of natural language and provide for a more complete description of the user's information need. We propose and analyze several novel algorithms dealing with long query information retrieval on the Web. These algorithms include selecting of search terms, constructing multiple query formulations, merging and ranking search results. We developed a meta-search engine, incorporating the proposed algorithms, and conducted a series of experiments to evaluate the performance of various algorithms. We also compared search results of the new engine with the results of popular search engines on the Web. These experiments clearly demonstrate that using long queries in the Web environment is practical and can substantially improve the quality of information retrieval.