As stated in
chapter 3, the sentence rank can significantly improve the linguistic
summarization other than the traditional TF or DF methods. Considering the complexity
in sentence rank, randomly pick a sentence and take the first 3 to 15 words
from the sentence within its original order as search query can avoid the
iterations in graph-based ranking algorithm, and the results below show that
even the sentences are randomly picked, when the number of terms up to 10, the
performance increases enormously, some of them are higher than 75%, which cannot
be accomplished easily by the previous carefully designed retrieval algorithms.
|
Random Sentence
|
Google
|
Yahoo
|
|
3
|
88.00
|
39.11%
|
90.00
|
40.00%
|
|
4
|
114.00
|
50.67%
|
102.00
|
45.33%
|
|
5
|
134.00
|
59.56%
|
124.00
|
55.11%
|
|
6
|
150.00
|
66.67%
|
144.00
|
64.00%
|
|
7
|
155.00
|
68.89%
|
137.00
|
60.89%
|
|
8
|
162.00
|
72.00%
|
154.00
|
68.44%
|
|
9
|
161.00
|
71.56%
|
144.00
|
64.00%
|
|
10
|
168.00
|
74.67%
|
151.00
|
67.11%
|
|
11
|
168.00
|
74.67%
|
151.00
|
67.11%
|
|
12
|
170.00
|
75.56%
|
168.00
|
74.67%
|
|
13
|
172.00
|
76.44%
|
168.00
|
74.67%
|
|
14
|
171.00
|
76.00%
|
169.00
|
75.11%
|
|
15
|
175.00
|
77.78%
|
174.00
|
77.33%
|
|
Average
|
152.92
|
67.97%
|
144.31
|
64.14%
|
Table4.24
(a) (b)
Figure4.26 Random Sentence Pick from Google and Yahoo results