INFORMATION RETRIEVAL TEST COLLECTIONS
- 1 January 1976
- journal article
- Published by Emerald Publishing in Journal of Documentation
- Vol. 32 (1) , 59-75
- https://doi.org/10.1108/eb026616
Abstract
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.Keywords
This publication has 19 references indexed in Scilit:
- Text searching retrieval of answer-sentences and other answer-passagesJournal of the American Society for Information Science, 1973
- Classification of scientific documents by means of self‐generated groups employing free languageJournal of the American Society for Information Science, 1973
- Document retrieval experiments using cluster analysisJournal of the American Society for Information Science, 1973
- CA Condensates as a retrospective search tool: A commentaryInformation Storage and Retrieval, 1973
- Term association analysis on a large file of bibliographic data, using a highly-controlled indexing vocabularyInformation Storage and Retrieval, 1973
- Evaluating the effectiveness of an on-line, natural language retrieval systemInformation Storage and Retrieval, 1972
- An experiment in index term frequencyJournal of the American Society for Information Science, 1972
- Retrieval efficiency from titles and the cost of indexingInformation Storage and Retrieval, 1971
- A highly associative document retrieval systemJournal of the American Society for Information Science, 1970
- Deriving term relations for a corpus by graph theoretical clustersJournal of the American Society for Information Science, 1970