On the delusiveness of adopting a common space for modeling IR objects: Are queries documents?

• Published in: Journal of the American Society for Information Science Vol. 44; no. 10; pp. 579 - 587
• Main Authors: Bollmann-Sdorra, Peter, Raghavan, Vijay V.
• Format: Journal Article
• Language: English
• Published: Washington, D.C Wiley Subscription Services, Inc., A Wiley Company 01.12.1993; John Wiley & Sons; American Documentation Institute
• Subjects: Computerized information storage and retrieval; Document Analysis; Documents; Exact sciences and technology; Examples; Information and communication sciences; Information Retrieval; Information retrieval systems. Information and document management system; Information science. Documentation; Linear Ordering; Mathematical Formulas; Measurement Techniques; Query formulation; Query Formulations; Sciences and techniques of general use; Similarity (Concept); Subject Index Terms; System design and modelling; Vector Model; Vector space models; Vector Spaces; Space; Question space; Separation; Query; Similarity; System design; Identification; Document; Research and development; Document space; Document retrieval; Documentation data processing; Vector space; Document retrieval system; Critical study; Models; Structure
• ISSN: 0002-8231; 1097-4571
• DOI: 10.1002/(SICI)1097-4571(199312)44:10<579::AID-ASI3>3.0.CO;2-B

Many authors, who adopt the vector space model, take the view that documents, terms, queries, etc., are all elements within the same (conceptual) space. This view seems to be a natural one, given that documents and queries have the same vector notation. We show, however, that the structure of the query space can be very different from that of the document space. To this end, concepts like preference, similarity, term independence, and linearity, both in the document space and in the query space, are discussed. Our conclusion is that a more realistic and complete view of IR is obtained if we do not consider documents and queries to be elements of the same space. This conclusion implies that certain restrictions usually applied in the design of an IR system are obviated. For example, the retrieval function need not be restricted to the ones that have the possibility to be interpreted as a similarity measure. © 1993 John Wiley & Sons, Inc.