C H A P T E R 2 1
I
n
f
o
r
m
a
t
i
o
n
R
e
t
r
i
e
v
a
l
E
x
e
r
c
i
s
e
s
21.1 Web keyword search systems depend critically on relative ranking of pages.
Earlier IR approaches were based on number of occurrences of each query
21.2 Information Retrieval.
a. Outline how documents are ranked using Term Frequency (TF) and In- verse
21.3 Suppose you are given an
e
n
t
r
o
p
y
function that gives a measure of how disor- dered
the elements of a set are: if all the elements belong to the same class the entropy is
0,
and if they are equally distributed amongst all classes, the entropy is 1.
Outline (in english) how a decision tree is constructed recursively, making
use of the entropy function.
. .
.5
21.4 Suppose use a
B
+
-tree to implement a text-indexing system. For each word, a list of
all documents containing the word is to be stored. Suppose that each document is
given a number (starting from 1) and a list of documents is repre- sented as an array
of bits, 1 indicating the document is in the list, and 0 indi- cating the document is not
in the list.
a. How can I get the list of all documents containing the words ”information”
and ”retrieval”?
. .
.3