IRS13 Thesaurus, Phrase and Hierarchy Dictionaries 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. VII-38 Number and Percentage Collection, Input Evaluation of Individual Requests and Type, Based on Thesaurus Average Rank Phrases Thesaurus Both Superior Superior Equal IRE-3, Abstract, First Rel. 4 11.8% 4 11.8% 26 76.5% Second Rel. 4 11.8% 8 23.5% 22 64.7% Thesaurus-3, 34 Requests Last Rel. 16 47.1% 14 41.2% 4 11.8% CRAN-l, Abstract, First Rel. 10 23.8% 12 28.6% 20 47.6% Second Rel.: 10 24.4% 15 36.6% 16 39.0% Thesaurus-3, 42 Requests Last Rel. 13 31.0% 16 38.1% 13 31.0% ADI, Text, Thesaurus-i First Rel. 3 8.6% 7 20.0% 25 71.4% Second Rel.t 12 38.7% 4 12.9% 15 48.4% 35 Requests Last Rel. 12 34.3% 13 37.1% 10 28.6% Hierarchy Thesaurus Both Superior Superior Equal 11Parent 5" First Rel. 5 14.7% 2 5.9% 27 79.4% Second Rel. 7 20.6% 7 20.6% 20 58.8% IRE-3, Abstract, Last Rel. 15 44.1% 19 55.9% 0 - Thesaurus-3, 34 Requests `1A11 Relations" First Rel. 6 17.6% 5 14.7% 23 67.6% Second Rel. 6 17.6% 13 38.2% 15 44.1% Last Rel. 13 38.2% 21 61.8% 0 - *:b In the Cran-1 Collection, 1 request has no second relevant, so results are based on 41 requests. # In the ADI collection, 4 requests have no second relevant so results are based on 31 requests. Comparison of Individ[OCRerr]a1 Request Merit giving the Number of Requests Favoring Thesaurus and Phrases, and Thesaurus and Hierarchy, according to Merit Assigned by the Average Ranks given in Fig. 25 Fig. 26