IRS13 Document Length chapter E. M. Keen Harvard University Gerard Salton Use, reproduction, or publication, in whole or in part, is permitted for any purpose of the United States Government. [OCRerr]rma I ized Recall .40[OCRerr] .35 .30 .25 `Is .10 .05 Title, Stem 0Title, Stem 0 Abstract, Stem Abstract, Stei Normalized x x Precision .30 - .25 0 F? 25 Requests superior on abstracts by amounts on plot 17 Requests superior on title, by amounts on plot .20 .15 .10 .05 Individual a5 Requests 0 x x In 18 24 RE 18 Requests superior on abstracts, by amounts on plot 24 Requests superior on titles, by amounts on plot CRAN-l, 42 Requests, Stem Dictionary, Overlap Correlation, Logical Vectors. Plots of the Magnitudes of the Differences of Individual Requests Comparing Abstracts and Titles, using the Normalized [OCRerr]Waluation Measures. Fig. 14