Robertson, S.E.; Walker, S.; Beaulieu, M.: Laboratory experiments with Okapi : participation in the TREC programme (1997)
0.01
0.009529176 = product of:
0.019058352 = sum of:
0.019058352 = product of:
0.038116705 = sum of:
0.038116705 = weight(_text_:systems in 2216) [ClassicSimilarity], result of:
0.038116705 = score(doc=2216,freq=2.0), product of:
0.16037072 = queryWeight, product of:
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.052184064 = queryNorm
0.23767869 = fieldWeight in 2216, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.0546875 = fieldNorm(doc=2216)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Briefly reviews the history of laboratory testing of information retrieval systems, focusing on the idea of a general purpose test collection of documents, queries and relevance judgements. Gives an overview of the methods used in TREC (Text Retrieval Conference) which is concerned with an ideal test collection, and discusses the Okapi team's participation in TREC. Also discusses some of the issues surrounding the difficult problem of interactive evaluation in TREC. The reconciliation of the requirements of the laboratory context with the concerns of interactive retrieval has a long way to go
