Automatic term class construction using relevance--A summary of work in automatic pseudoclassification

Abstract Term classifications and thesauri can be used for many purposes in automatic information retrieval. Normally a thesaurus is generated manually by subject experts: alternatively, the associations between the terms can be obtained automatically by using the occurrence characteristics of the terms across the documents of a collection. A third possibility consists in taking into account user relevance assessments of certain documents with respect to certain queries in order to build term classes designed to retrieve the relevant documents and simultaneously to reject the nonrelevant documents. This last strategy, known as pseudoclassification, produces a user-dependent term classification. A number of pseudoclassification studies are summarized in the present report, and conclusions are reached concerning the effectiveness and feasibility of constructing term classifications based on human relevance assessments.

[1]  Aviezri S. Fraenkel,et al.  Local Feedback in Full-Text Retrieval Systems , 1977, JACM.

[2]  Stephen E. Robertson,et al.  Relevance weighting of search terms , 1976, J. Am. Soc. Inf. Sci..

[3]  Gerard Salton,et al.  Dynamic information and library processing , 1975 .

[4]  Gerard Salton,et al.  Generation and search of clustered files , 1978, TODS.

[5]  Vijay V. Raghavan,et al.  Experiments on the determination of the relationships between terms , 1978, SIGIR 1978.

[6]  Clement T. Yu,et al.  Precision Weighting—An Effective Automatic Indexing Method , 1976, J. ACM.

[7]  Clement T. Yu,et al.  A Statistical Model for Relevance Feedback in Information Retrieval , 1976, JACM.

[8]  Barry Litofsky,et al.  Utility of automatic classification systems for information storage and retrieval , 1969 .

[9]  Robert N. Oddy,et al.  INFORMATION RETRIEVAL THROUGH MAN‐MACHINE DIALOGUE , 1977 .

[10]  Gerard Salton,et al.  Experiments in Automatic Thesaurus Construction for Information Retrieval , 1971, IFIP Congress.

[11]  Carlo Vernimb,et al.  Automatic query adjustment in document retrieval , 1977, Inf. Process. Manag..

[12]  Michael E. Lesk,et al.  Computer Evaluation of Indexing and Text Processing , 1968, JACM.

[13]  Vijay V. Raghavan,et al.  Experiments on the determination of the relationships between terms , 1979, ACM Trans. Database Syst..

[14]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[15]  Clement T. Yu.  A methodology for the construction of term classes , 1974, Inf. Storage Retr..

[16]  John H. Williams,et al.  Functions of a Man-Machine Interactive Information Retrieval System. , 1971 .

[17]  Clement T. Yu.  A Formal Construction of Term Classes , 1975, JACM.

[18]  David M. Jackson,et al.  The construction of retrieval environments and pseudo-classifications based on external relevance , 1970, Inf. Storage Retr..