IRS13
Scientific Report No. IRS-13 Information Storage and Retrieval
An Experiment in Automatic Thesaurus Construction
chapter
R. T. Dattola
D. M. Murray
Harvard University
Gerard Salton
Use, reproduction, or publication, in whole or in part, is permitted for any purpose of the United States Government.
VIII-7
D D D D D D
1 2 3 4 5 6
Cl 1 o 0 0 0 0
C2 1 o 1 0 0 0
C3 1 o 1 0 0 0
C4 0 1 0 1 1 1
C5 0 1 0 1 0 1
C6 0 1 0 1 0 0
C7 0 o 1 0 0 0
C8 0 0 0 1 0 0
Cl
C2
C3
C
4
Cs
C6
C7
C
8
(a) Concept-Document Matrix
C C C C C C C C8
1 2 3 4 5 6 7
1.0 .70 .70 0 0 0 0 0
.70 1.0 1.0 0 0 0 .70 0
.70 1.0 1.0 0 0 0 .70 0
0 0 0 1.0 .86 .70 0 .50
0 0 0 .86 1.0 .81 0 .57.
0 0 0 .70 .81 1.0 0 .70
0 .70 .70 0 0 0 1.0 0
0 0 0 .50 .57 .70 0 1.0
(b) Concept-Concept Similarity Matrix Cosine Correlation
Construction of Concept - Concept. Similarity Matrix
Fig. 1