ISR10 Scientific Report No. ISR-10 Information Storage and Retrieval Table of Contents table of contents Joseph John Rocchio Harvard University Gerard Salton Use, reproduction, or publication, in whole or in part, is permitted for any purpose of the United States Government. TABLE OF CO[OCRerr][OCRerr]S [OCRerr]a[OCRerr]e Pre~ace List o[OCRerr] Fi[OCRerr]es List of Tables Synopsis V * . . xl * . * . xlii * * . xv CIIAPTER 1 I[OCRerr]RODUCTIO[OCRerr] 1-1 1. The Document Retrieval Problem 1-1 2. A Functional [OCRerr]o[OCRerr]el 1-2 3. A Specific Mo[OCRerr]el - The S[OCRerr]T System 1-6 A. Property Vector In[OCRerr]exing 1-6 B. Request Processin[OCRerr] 1-7 C. A[OCRerr]ig[OCRerr]ilar Distance Matchin[OCRerr] 1-7 D. Terminology 1-8 C[OCRerr]ABTER 2 [OCRerr]B:8 I[OCRerr]EXlN[OCRerr] FUNCTION 2-1 1. Intro[OCRerr]uction 2-1 2. Manual In[OCRerr]exing 2-2 3. Automatic In[OCRerr]exirig 2-2 A. The Statistical Approach 2-3 B. Semantic Techniq[OCRerr]es 2-4 C. Syntactic Techni3ques 2-6 4. The Structure of In[OCRerr]ex Representations 2-8 5. Optimizin[OCRerr][OCRerr]the In&ex Transformation 2-1.2 vii