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. rmolized Recoil Text, Stem 0 .28 .24 x .20 .16 .12 .08 x Cp[OCRerr] .04 0 O[OCRerr]O Abstroct1 Stem Normalized Precision .52[OCRerr] .44 I Abstroct1 St Text, Stem .32 0 .28 .24 .20 [OCRerr] .16 \ \ .12 .08 N)[OCRerr]'kOA .04 14 19 Individual Requests 19 Requests superior in Text, by amounts on plot 14 Requests superior on Abstracts, by amounts on plot 1 Request equal on both I? 18 17 Requests superior on Text, by amounts on 18 Requests superior on Abstracts, by amoun plot 1 Request equal on both ADI, 35 Requests, Stem Dictionary. Plot of the Magnitudes of the i)ifferences of Individual Requests Comparing Full Text and Abstracts, using the Normalized L'Valuation Measures. Fig. 22.