<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>Appendix D Results of the GeoCLEF Track</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Giorgio Maria Di Nunzio</string-name>
          <email>dinunzio@dei.unipd.it</email>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Nicola Ferro</string-name>
          <email>ferro@dei.unipd.it</email>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Department of Information Engineering University of Padua Italy</institution>
        </aff>
      </contrib-group>
      <fpage>337</fpage>
      <lpage>378</lpage>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Introduction
3</p>
      <p>Results for CLEF 2006 GeoCLEF Tracks
List of Submitted Experiments
7
berkeley
berkeley
daedalus
daedalus
daedalus
daedalus
daedalus
hagen
hagen
hagen
hagen
hagen
hildesheim
hildesheim
hildesheim
hildesheim
alicante
alicante
alicante
alicante
berkeley
berkeley
berkeley
berkeley
daedalus
daedalus
daedalus
daedalus
daedalus
hildesheim
hildesheim
hildesheim
hildesheim
hildesheim
imp-coll
imp-coll
jaen
jaen
jaen
jaen
jaen
ms-china
ms-china
ms-china
ms-china
ms-china
nicta
nicta
nicta
nicta
nicta
rfia-upv
rfia-upv
rfia-upv
rfia-upv
sanmarcos</p>
      <p>TDN
TD
TD
TDN
TDN
TD
TDN
TD
TD
TDN
TDN
TDN
TDN
TD
TD
TDN
TD
TDN
TDN
TDN
TDN
TDN
TDN
TD
TDN
TD
TD
TDN
TDN
TDN
TDN
TD
TD
TD
TDN
TD
TD
TDN
TD
TD
TD
TD
T
TD
T
TDN
TDN
TDN
TD
TD
TD
TD
TDN
TD
TDN
TD
sanmarcos
sanmarcos
sanmarcos
sanmarcos
talp
talp
talp
talp
talp
u.buffalo
u.buffalo
u.buffalo
u.buffalo
u.groningen
u.groningen
u.groningen
u.groningen
u.groningen
u.twente
u.twente
u.twente
u.twente
u.twente
unsw
unsw
unsw
unsw
unsw
xldb
xldb
xldb
xldb
xldb
alicante
alicante
alicante
berkeley
berkeley
daedalus
daedalus
daedalus
daedalus
daedalus
sanmarcos
sanmarcos
sanmarcos
sanmarcos
sanmarcos
berkeley
berkeley
berkeley
berkeley
sanmarcos
sanmarcos
sanmarcos
sanmarcos</p>
      <p>AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
MANUAL
AUTOMATIC
MANUAL
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
MANUAL
MANUAL
MANUAL
MANUAL
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
no
yes
no
yes
no
yes
yes
no
no
no
yes
no
yes
yes
yes
no
no
no
yes
yes
no
yes
no
yes
yes
no
no
no
no
no
no
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes</p>
      <p>MANUAL
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
no
no
no
yes
no
no
no
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
yes
Track Overview Results and Graphs
13
v 40%
A
30%
20%
10%
0%</p>
      <p>0%
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
−1
026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
Topic Identifier
FUHddGYYYTD [MAP 22.29%; Pooled]</p>
      <p>FUHddGYYYTDN [MAP 21.41%; Pooled]
FUHddGYYYMTDN [MAP 19.99%; Pooled]</p>
      <p>BKGeoD2 [MAP 18.22%; Pooled]
FUHddGNNNTD [MAP 16.94%; Pooled]</p>
      <p>HIGeodederun4n [MAP 16.01%; Pooled]
tsn HIGeodederun4 [MAP 15.58%; Pooled]
e
m
i
r
e
xpE FUHddGNNNTDN [MAP 12.23%; Pooled]</p>
      <p>HIGeodederun6 [MAP 12.14%; Pooled]
HIGeodederun6n [MAP 11.34%; Pooled]</p>
      <p>GCdeNtLg [MAP 10.01%; Pooled]</p>
      <p>GCdeNA [MAP 9.28%; Pooled]
GCdeAtLg [MAP 7.36%; Pooled]</p>
      <p>GCdeAA [MAP 7.15%; Pooled]
GCdeAO [MAP 5.48%; Pooled]
0%
10%
20%
30% 40% 50% 60% 70%</p>
      <p>Mean Average Precision
80%</p>
      <p>90% 100%</p>
      <p>GeoCLEF Monolingual German track − Tukey T test with "top group" highlighted
BKGeoD1</p>
      <p>FUHddGNNNTD
HIGeodederun4n
40%
30%
20%
10%
0%</p>
      <p>5
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
−1
026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
Topic Identifier</p>
      <p>FUHddGYYYTD [R−Prec 21.53%; Pooled]</p>
      <p>FUHddGYYYTDN [R−Prec 20.56%; Pooled]
FUHddGYYYMTDN [R−Prec 20.39%; Pooled]</p>
      <p>BKGeoD1 [R−Prec 19.99%; Pooled]</p>
      <p>BKGeoD2 [R−Prec 18.57%; Pooled]
HIGeodederun4 [R−Prec 18.15%; Pooled]</p>
      <p>FUHddGNNNTD [R−Prec 18.00%; Pooled]</p>
      <p>HIGeodederun6 [R−Prec 13.45%; Pooled]
FUHddGNNNTDN [R−Prec 13.40%; Pooled]</p>
      <p>GCdeNtLg [R−Prec 11.53%; Pooled]</p>
      <p>GCdeNA [R−Prec 10.19%; Pooled]</p>
      <p>GCdeAA [R−Prec 8.93%; Pooled]
GCdeAtLg [R−Prec 8.78%; Pooled]</p>
      <p>GCdeAO [R−Prec 6.62%; Pooled]
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>R−Precision</p>
      <p>GeoCLEF Monolingual German track − Tukey T test with "top group" highlighted
FUHddGYYYTD</p>
      <p>BKGeoD2
FUHddGNNNTDN
HIGeodederun6n
HIGeodederun6</p>
      <p>GCdeNtLg</p>
      <p>GCdeNA
GCdeAtLg</p>
      <p>GCdeAA
GCdeAO
0.05
0.0806 Spanish-English using all topic fields and other
0.2164 sources</p>
      <p>GeoCLEF Bilingual English track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
itfcsoep45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual English track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftcsope45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Precision averages (%) for individual
queries
Topic 026 6.35
Topic 027 1.18
Topic 028 11.57
Topic 029 21.08
Topic 030 100.00
Topic 031 13.41
Topic 032 91.32
Topic 033 0.46
Topic 034 42.42
Topic 035 2.10
Topic 036 0.00
Topic 037 1.60
Topic 038 0.56</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
16.01
26.20
0.23
0.82
1.67
22.48
1.67
69.30
3.44
70.96
33.33
23.43
1
0.8
0.6
0.4
0.2</p>
      <p>GeoCLEF Bilingual English track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
0%5
Precision averages (%) for individual
queries
Topic 026 11.11
Topic 027 5.26
Topic 028 10.53
Topic 029 22.22
Topic 030 100.00
Topic 031 13.56
Topic 032 80.65
Topic 033 0.00
Topic 034 33.33
Topic 035 0.00
Topic 036 0.00
Topic 037 6.25
Topic 038 0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
12.50
21.43
0.00
0.00
0.00
34.21
0.00
66.67
8.33
72.92
50.00
33.33
1
0.8
0.6
0.4
0.2</p>
      <p>GeoCLEF Bilingual English track − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual English track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftscope45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.01
0.84
11.51
25.94
0.00
65.65
97.82
2.12
13.61
0.71
2.96
6.28
6.63</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
0.98
56.39
22.43
35.55
0.13
18.03
5.67
61.44
28.60
82.80
78.74
17.96
1
0.8
0.6
0.4
0.2</p>
      <p>GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftcspoe45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
0%5
GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
Exact R-Precision
Maximum
Minimum
First Quartile
Second Quartile
Third Quartile
Interquartile range
Mean
Standard Deviation
Lower Outlier Threshold
Upper Outlier Threshold
Mean With No Outliers
Std With No Outliers
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
0.00
5.56
30.30
0.00
67.45
90.00
3.00
13.51
0.00
6.36
0.00
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
2.99
61.87
34.67
39.62
0.00
28.16
16.67
60.71
33.90
73.96
70.51
22.00
1
0.8
0.6
0.4
0.2</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
0.0421 EN-&gt;ES using L&amp;H query translation. title, desc
0.2882 and narrative
GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.11
38.67
10.67
47.52
0.00
62.41
97.40
1.53
9.83
2.03
0.02
0.00
0.93</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
53.58
67.60
16.07
47.96
3.18
2.83
1.38
63.69
0.97
73.23
74.35
10.18
1
0.8
0.6
0.4
0.2</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
60%
0%5
Exact R-Precision
Maximum
Minimum
First Quartile
Second Quartile
Third Quartile
Interquartile range
Mean
Standard Deviation
Lower Outlier Threshold
Upper Outlier Threshold
Mean With No Outliers
Std With No Outliers
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
41.03
13.89
54.55
0.00
60.39
90.77
4.00
13.51
5.26
0.00
0.00
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
50.75
68.35
18.67
50.94
4.17
7.77
0.00
53.57
1.69
63.02
69.59
4.00
1
0.8
0.6
0.4
0.2
10
t
n
e
irm8
xep
E
the 6
f
so
c
iop 4
T
f
o
r
e
b 2
m
u
N</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Priority</p>
      <p>Query Construction
25,000 Source Language
2,054 Topic Fields
729 Pooled
0.0291 Automatic English Spanish title + desc
0.1505
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
2.12
2.04
24.55
0.98
13.11
1.02
19.71
0.01
15.87
9.91
11.02
11.45
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
16.72
54.13
0.86
20.06
0.00
29.54
2.21
11.07
6.94
5.81
57.45
4.01
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
10
t
n
e
irm8
xep
E
the 6
f
so
c
iop 4
T
f
o
r
e
b 2
m
u
N</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
60%
0%5
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
2.56
27.78
3.03
17.88
5.10
20.77
0.00
18.92
15.79
22.73
17.24
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
23.88
61.15
6.67
28.30
0.00
37.86
0.00
14.29
11.86
7.55
66.82
12.00
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8</p>
      <p>GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftscope45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Priority</p>
      <p>Query Construction
25,000 Source Language
2,054 Topic Fields
659 Pooled
2
AUTOMATIC
Portuguese
title, description
true
0.0221 Automatic Portuguese Spanish title+desc
0.1261
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
1.72
3.17
7.13
28.54
0.29
0.87
19.83
0.09
21.30
2.99
0.68
0.05
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
27.01
53.35
1.00
31.64
0.03
5.52
2.29
5.19
3.17
5.65
45.66
5.21
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xep
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
60%
0%5
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
5.56
12.82
13.89
30.30
2.65
5.10
20.77
1.00
29.73
5.26
3.64
0.00
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
23.88
60.43
9.33
37.74
0.00
14.56
8.33
7.14
3.39
7.55
55.76
8.00
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8</p>
      <p>GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
itfscoep45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Priority</p>
      <p>Query Construction
25,000 Source Language
2,054 Topic Fields
655 Pooled
3
AUTOMATIC
Portuguese
title, description, narrative
true
0.0230 Automatic Portuguese Spanish title-desc-narr
0.1310
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
1.78
2.67
8.07
32.55
0.28
1.43
20.01
0.06
23.16
4.01
0.72
0.05
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
27.15
53.78
0.99
31.54
0.03
5.84
2.15
5.76
3.37
5.68
51.21
5.28
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xpe
E10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
60%
30%
20%
10%
0%5
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
5.56
12.82
16.67
30.30
2.65
6.67
20.77
1.00
40.54
5.26
3.64
0.00
0.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
25.37
60.43
9.33
37.74
0.00
15.53
0.00
7.14
3.39
7.55
59.45
10.00
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8</p>
      <p>GeoCLEF Bilingual Spanish track − Box plot of the Topics of the Experiment
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision</p>
      <p>GeoCLEF Bilingual Spanish track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftsceop54
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Overall statistics for 25 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
      <p>Query Construction
25,000 Source Language
1,060 Topic Fields
591 Pooled
0.0098 EN-&gt;PT using L&amp;H query translation. title and
0.1291 description used
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
1.22
0.03
12.27
27.03
0.81
43.74
14.19
0.00
0.14
0.55
0.00
1.29
14.35</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
5.45
0.01
0.01
10.65
2.46
0.00
27.39
33.97
0.13
79.32
24.37
15.70
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xep
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
60%
30%
20%
10%
0%5
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Exact R-Precision
Maximum
Minimum
First Quartile
Second Quartile
Third Quartile
Interquartile range
Mean
Standard Deviation
Lower Outlier Threshold
Upper Outlier Threshold
Mean With No Outliers
Std With No Outliers
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
0.00
21.88
33.33
0.00
39.34
26.42
0.00
0.00
0.00
0.00
0.00
12.50</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
8.70
0.00
0.00
20.00
4.17
0.00
36.59
37.88
0.00
73.43
27.78
27.27
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xep
E10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Overall statistics for 25 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
      <p>Query Construction
25,000 Source Language
1,060 Topic Fields
630 Pooled
0.0114 EN-&gt;PT using L&amp;H query translation. title, desc and
0.1422 narrative
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
1.27
8.97
24.05
33.34
0.69
21.61
7.76
0.00
0.15
0.14
0.00
0.07
18.63</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
8.98
0.01
0.00
43.84
6.26
0.00
24.53
51.65
2.96
69.74
8.80
24.03
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xpe
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
Docs Cutoff Levels Precision at DCL (%)
5 docs 24.80
10 docs 22.80
15 docs 22.67
20 docs 20.80
30 docs 19.73
100 docs 13.36
200 docs 9.14
500 docs 4.55
1000 docs 2.52
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
16.34
100%
90%
80%
70%
60%
30%
20%
10%
0%5
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Exact R-Precision
Maximum
Minimum
First Quartile
Second Quartile
Third Quartile
Interquartile range
Mean
Standard Deviation
Lower Outlier Threshold
Upper Outlier Threshold
Mean With No Outliers
Std With No Outliers
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
20.59
34.38
38.46
0.00
21.31
20.75
0.00
0.00
0.00
0.00
0.00
12.50</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
13.04
0.00
0.00
42.86
8.33
0.00
35.37
54.55
0.00
64.34
5.56
36.36
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xpe
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Overall statistics for 25 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved</p>
      <p>Priority</p>
      <p>Query Construction
25,000 Source Language
1,060 Topic Fields</p>
      <p>608 Pooled
0.0511 Spanish-Portuguese
0.1174
1
MANUAL
Spanish; Castilian
title, description
true
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
1.17
6.97
8.54
6.86
38.66
14.38
49.84
1.16
2.24
2.47
2.88
0.14
30.10</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
30.28
1.41
1.15
49.61
0.11
7.75
2.95
25.94
8.84
2.29
14.11
10.34
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
xep
E10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
Docs Cutoff Levels Precision at DCL (%)
5 docs 23.20
10 docs 21.60
15 docs 18.67
20 docs 17.40
30 docs 16.00
100 docs 9.88
200 docs 6.52
500 docs 3.97
1000 docs 2.43
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
14.88
100%
90%
80%
70%
60%
30%
20%
10%
0%5</p>
      <p>GeoCLEF Bilingual Portuguese track − Retrieved documents vs Precision
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Exact R-Precision
Maximum
Minimum
First Quartile
Second Quartile
Third Quartile
Interquartile range
Mean
Standard Deviation
Lower Outlier Threshold
Upper Outlier Threshold
Mean With No Outliers
Std With No Outliers
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
0.00
12.75
15.62
7.69
42.86
13.11
58.49
0.00
0.00
0.00
0.00
0.00
25.00</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
26.09
4.17
2.88
48.57
0.00
10.53
8.54
33.33
8.82
9.79
27.78
15.91
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
10
t
n
e
irm8
xep
E
the 6
f
so
c
iop 4
T
f
o
r
e
b 2
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision
Overall statistics for 25 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
      <p>Query Construction
25,000 Source Language
1,060 Topic Fields
655 Pooled
0.0497 Automatic Spanish Portuguese title + desc
0.1415
100%
90%
80%
70%
30%
20%
10%</p>
      <p>GeoCLEF Bilingual Portuguese track − Interpolated Recall vs Average Precision
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>Interpolated Recall
GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038
7.79
0.16
13.15
23.65
1.64
16.14
75.79
0.17
3.21
2.76
1.92
1.72
16.26</p>
      <p>Topic 039
Topic 040
Topic 041
Topic 042
Topic 043
Topic 044
Topic 045
Topic 046
Topic 047
Topic 048
Topic 049
Topic 050
8.25
2.84
1.12
25.88
0.02
7.97
23.82
9.22
5.42
51.93
39.97
13.12
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
10
t
n
e
irm8
xpe
E
the 6
f
so
c
iop 4
T
f
o
r
e
b 2
m
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Mean Average Precision
SMGeoESPT2
100%
90%
80%
70%
60%
Precision averages (%) for individual
queries
Topic 026
Topic 027
Topic 028
Topic 029
Topic 030
Topic 031
Topic 032
Topic 033
Topic 034
Topic 035
Topic 036
Topic 037
Topic 038</p>
      <p>GeoCLEF Bilingual Portuguese track − Retrieved documents vs Precision</p>
      <p>GeoCLEF Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual Portuguese track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
iftcspoe45
h
fo3
T
o
r2
e
b
m
u1
N
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      <p>Exact R−Precision</p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          <source>0.0512 Automatic Spanish English title+des 0</source>
          .
          <source>2039</source>
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>