Search results

The evaluation of information retrieval systems has recently become an important matter. In the past, however, most reports or proposals on this type of work appear largely to have ignored the efficiency of operation of the central core of an IR system, namely those operations concerned in the compilation and use of the index. The only aspects to receive consideration are the physical form of the index and the design of thesauri or classifications. The former activity has been slanted towards the use of computers and has tended to assume that this type of equipment will, ipso facto, give an improved performance but has made no attempt to justify cost factors which may be one hundred times that of conventional techniques. Work on thesauri and classifications, where it has been practical in nature, appears to consist of compiling lists of terms which go out of favour as quickly as any list of subject headings in the past; the more popular theoretical approach is the setting up of models or the use of increasingly abstruse and complex algebras. From the results and conclusions of the experimental work at Cranfield, it would seem that many of these investigations are comparatively trivial.

Reports a laboratory comparison of the effectiveness and efficiency of five index languages in the subject area of library and information science; three post‐co‐ordinate languages, Compressed Term, Uncontrolled, and Hierarchically Structured, and two pre‐co‐ordinate ones, Hierarchically Structured and Relational Indexing. Eight test comparisons were made, and factors studied were index language specificity and linkage, indexing specificity and exhaustivity, method of co‐ordination, the precision devices of partitioning and relational operators, and the provision of context in the search file. Full details of the test and retrieval results are presented.

This paper seeks to examine image retrieval within two different contexts: a monolingual context where the language of the query is the same as the indexing language and a multilingual context where the language of the query is different from the indexing language. The study also aims to compare two different approaches for the indexing of ordinary images representing common objects: traditional image indexing with the use of a controlled vocabulary and free image indexing using uncontrolled vocabulary.

This research uses three data collection methods. An analysis of the indexing terms was employed in order to examine the multiplicity of term types assigned to images. A simulation of the retrieval process involving a set of 30 images was performed with 60 participants. The quantification of the retrieval performance of each indexing approach was based on the usability measures, that is, effectiveness, efficiency and satisfaction of the user. Finally, a questionnaire was used to gather information on searcher satisfaction during and after the retrieval process.

The results of this research are twofold. The analysis of indexing terms associated with all the 3,950 images provides a comprehensive description of the characteristics of the four non‐combined indexing forms used for the study. Also, the retrieval simulation results offers information about the relative performance of the six indexing forms (combined and non‐combined) in terms of their effectiveness, efficiency (temporal and human) and the image searcher's satisfaction.

The findings of the study suggest that, in the near future, the information systems could benefit from allowing an increased coexistence of controlled vocabularies and uncontrolled vocabularies, resulting from collaborative image tagging, for example, and giving the users the possibility to dynamically participate in the image‐indexing process, in a more user‐centred way.

The paper describes some properties of simple interconversion devices which enable material intially subject indexed by a particular indexing system to be made available to other institutions using different indexing languages in such a form as to be readily integrated into their indexes. Reference is made to the outline Intermediate Lexicon which is the germinal form of a switching language for the field of information science. Difficulties and problems in effecting satisfactory information transfer through such an interconversion scheme are explored, and suggestions made for the lines upon which further research needs to be undertaken. The author was the Classification Research Group representative on the international working party concerned with the Intermediate Lexicon.

Experimental evidence suggests that enhancing the subject content of OPAC records can improve retrieval performance. This is based on the use of natural language index terms derived from the table of contents and back‐of‐the‐book index of documents. The research reported here investigates the alternative approach of translating these natural language terms into controlled vocabulary. Subject queries were collected by interview at the catalogue, and indexing of the queries demonstrated the impressive ability of PRECIS, and to a lesser extent LCSH, to represent users' information needs. DDC performed poorly in this respect. The assumption was made that an index language adequately specific to represent users' queries should be adequate to represent document contents. Searches were carried out on three test databases, and both natural language and PRECIS enhancement of MARC records increased the number of relevant documents found, with PRECIS showing the better performance. However, with weak stemming the advantage of PRECIS was lost. Consideration must also be given to the potential advantages of controlled vocabulary, over and above basic retrieval performance measures.

This paper explains at least some of the major problems related to the subject indexing process and proposes a new approach to understanding the process, which is ordinarily described as a process that takes a number of steps. The subject is first determined, then it is described in a few sentences and, lastly, the description of the subject is converted into the indexing language. It is argued that this typical approach characteristically lacks an understanding of what the central nature of the process is. Indexing is not a neutral and objective representation of a document’s subject matter but the representation of an interpretation of a document for future use. Semiotics is offered here as a framework for understanding the “interpretative” nature of the subject indexing process. By placing this process within Peirce’s semiotic framework of ideas and terminology, a more detailed description of the process is offered which shows that the uncertainty generally associated with this process is created by the fact that the indexer goes through a number of steps and creates the subject matter of the document during this process. The creation of the subject matter is based on the indexer’s social and cultural context. The paper offers an explanation of what occurs in the indexing process and suggests that there is only little certainty to its result.

This article reviews the state of the art in automatic indexing, that is, automatic techniques for analysing and characterising documents, for manipulating their descriptions in searching, and for generating the index language used for these purposes. It concentrates on the literature from 1968 to 1973. Section I defines the topic and its context. Sections II and III consider work in syntax and semantics respectively in detail. Section IV comments on ‘indirect’ indexing. Section V briefly surveys operating mechanized systems. In Section VI major experiments in automatic indexing are reviewed, and Section VII attempts an overall conclusion on the current state of automatic indexing techniques.

This approach to co‐operation between libraries and information centres considers the use of switching languages. These can be employed in situations where several centres with a common interest wish to co‐operate in the collection and indexing of information bearing material, yet prefer to retain the systems often developed and tailored to their individual requirements. To facilitate the exchange of subject information between the centres, a series of concordances are constructed between each of the indexing languages and the switching language. Thus the translation of subject indexing expressed in the indexing languages of the other participating centres can then proceed automatically. Among the possible benefits are the economic saving due to the sharing by several centres in the collection and indexing of material, and the increase in coverage enjoyed by all the centres. To determine the feasibility of such devices, a switching language, the Intermediate Lexicon for Information Science, has been developed and is under test at the Polytechnic of North London School of Librarianship. The work is supported by a grant from British Library Research and Development Department.

Many retrieval experiments have been based on inadequate test collections, and current research is hampered by the lack of proper collections. This short review does not attempt a fully documented survey of all the collections used in the past decade: hopefully representative examples have been studied to throw light on the requirements test collections should meet, to show how past collections have been defective, and to suggest guidelines for a future ‘ideal’ test collection. The specifications for this collection can be taken as an indirect comment on our present state of knowledge of major retrieval system variables, and experience in conducting experiments.

This paper examines the implications of the findings of evaluative tests regarding the retrieval performance of natural language in various subject fields. It suggests parallel investigations into the structure of natural language, with particular reference to terminology, as used in the different branches of basic science. The criteria for defining the terminological consistency of a subject are formulated and a measure suggested for determining the degree of terminological consistency.