Query operations of process-based searches

Abstract

This paper introduces a non-traditional Web search problem, referred to as “process-based search”, and focuses on the query analysis and formulation of this type of search. Traditional information retrieval models were created based on the assumption that one query can be answered by one document. A query needs to properly specify the topic being requested. Recently published work, referred to as subtopic retrieval or aspect retrieval, has relaxed this assumption that a query may contain multiple subtopics and it can be answered by a set of documents, each of which covers one or multiple subtopics. However, the original query was still assumed to explicitly specify the subtopics. Process-based search further relaxes the assumption to facilitate complex Web searches. The subtopics of the query do not have to be explicitly specified, because the user may not be able to do so in the initial search due to the lack of knowledge for the topic. A database of processes is used to discover the subtopics implied by the query. Thus, this type of search is called process-based search. This paper focuses on the algorithms for formulating sub-queries for the process-based search. Experiments on real data sets showed that the needs of process-based searching exist in the real world and the proposed concepts and approaches effectively solve this problem.