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. EVALUATION NUMBER OF INDIVIDUAL REQUESTS COLLECTION DICTIONARY MEASURE USED TEXT,ABS. TO DETERMINE TEXT ABSTRACT TITLE AND TITLE MERIT SUPERIOR SUPERIOR S[OCRerr]ERIOR EQUAL ADI Stem Normed. Recall 16 (47.1%) 13 (38.2%) 5 (i4.[OCRerr]) 0 Normed. Precision 15 (44.1%) ih (41.2%) 5 (i4.[OCRerr]) 0 35 Requests Thesaurus-i Normede Recall 17 (53.1%) 10 (31.3%) 5 (15.6%) 1 Normed. Precision 17 (51.5%) 9 (27.3%) 7 (21e2%) 1 Comparisons of individual request merit giving the numbers of requests favoring full text, abstracts and titles, using two dictionaries, according to merit assigned by the normalized evaluation measures. Figure 24.