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. lormolized Recoil .24 I .20 16 12 x Abstracts, Thesaurus 2 Indexing, Thesaurus -2 x 08 04 xx Individual Requests 0 16 23 23 Requests superior on Indexing, by amounts in plot 16 Requests superior on Abstracts, by amounts in plot 3 Requests equal on both Normalized Precision .40[OCRerr] .28 .24 .20 .16 x .12 .08 .04 0 15 25 Abstracts, Thes Indexing, Thesa mdi Req[OCRerr] 23 Requests superior on Indexing, by amounts in plot 15 Reque[OCRerr]ts superior on Abstracts, by amounts in plot 4 Requests equal on both CRAN-l, 42 Requests, Thesaurus-2 (New Quasi-Synonym) Dictionary. Plots of the Magnitudes of the Differences of Individual Requests C[OCRerr]nparing Indexing and Abstracts, using the Normalized EWaluation Measures. Fig. 31.