<!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>382</fpage>
      <lpage>423</lpage>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Introduction
3</p>
      <p>Results for CLEF 2007 GeoCLEF Track
3. Individual Experiment Results and Graphs
This section provides the individual results for each official experiment. For each experiment the following tables and graphs are
shown:
- Overall statistics and information
- Interpolated recall vs precision averages plot
- Average precision statistics and box plot
- Average precision comparison to median plot
- Document cutoff levels vs precision at DCL plot
- R-Precision statistics and box plot
- R-Precision comparison to median plot
Topics are identified with DOIs, as well as the experiments. The prefix for the DOI of a topic is 10.2452. The following example
shows how to build the DOI for a topic given its number: for topic 200-AH, the corresponding DOI is 10.2452/200-AH
List of Submitted Experiments
7</p>
    </sec>
    <sec id="sec-2">
      <title>GC-MONO-DE-CLEF2007</title>
      <p>de
de
de
de
de
de
de
de
de
de
de
de
de
es
es
es
en
en
es
en
en
en
en
en
en
en
en
en
en
en
en
en
en
es
es
en
en
en
en
en
TD
TD
TDN
TD
TD
TDN
TDN
TD
TD
TD
TDN
TDN
TD
TD
TDN
TD
TD
TD
TDN
TDN
TDN
TD
TD
TDN
TD
TD
TDN
TDN
T
TD
TDN
TDN
TDN
TD
TDN
TD
TD
TDN
TDN
TDN
no
no
no
yes
yes
yes
yes
no
TDN
MANUAL
no
icl
linguit
linguit
linguit
linguit
moscow
moscow
msasia
msasia
msasia
msasia
msasia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
valencia
en
en
en
en
en
es
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
pt
es
pt
pt
pt
pt
pt
pt
pt
pt
pt
T
TD
T
T
TD
TN
TD
TDN
TD
TDN
TD
TD
TDN
TD
TDN
TD
TDN
TD
TD
TD
TD
TD
TD
TD
T
T
T
T
TD
TD
TD
TDN
TD
TDN
TD
T
T
T
T
yes
yes
no
no
no
yes
yes
yes
yes
yes</p>
    </sec>
    <sec id="sec-3">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-4">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-5">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-6">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-7">
      <title>AUTOMATIC</title>
      <p>csusm</p>
    </sec>
    <sec id="sec-8">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-9">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-10">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-11">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-12">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-13">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-14">
      <title>GC-BILI-X2DE-CLEF2007</title>
    </sec>
    <sec id="sec-15">
      <title>GC-BILI-X2DE-CLEF2007</title>
      <p>Track Overview Results and Graphs
12
30%
20%
10%
0%</p>
      <p>0%
1
0.8
0.6
0.4
0.2
e
c
n
re 0
e
iff
D
−0.2
−0.4
−0.6
−0.8
−1
51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC
Topic Identifier
GeoCLEF Monolingual German Task − Box Plot of the Topics
hildesheim [Experiment HIMODENE2NA; MAP 20.67%; Pooled]
csusm [Experiment GEOMODE6; MAP 20.38%; Pooled]
csusm [Experiment GEOMODE1; MAP 20.38%; Pooled]
s
t
n
e
m
i
r
e
p
x
E
hildesheim [Experiment HIMODEBASE; MAP 20.19%; Pooled]</p>
      <p>hagen [Experiment FUHTD6DE; MAP 19.57%; Pooled]
hildesheim [Experiment HIMODENE2; MAP 19.53%; Pooled]
hagen [Experiment FUHTD2DE; MAP 19.11%; Pooled]
hagen [Experiment FUHTD3DE; MAP 19.09%; Pooled]
hildesheim [Experiment HIMODENE3; MAP 17.95%; Pooled]
cheshire [Experiment BERKMODEBASE; MAP 13.92%; Pooled]
csusm [Experiment GEOMODE3; MAP 11.70%; Pooled]
csusm [Experiment GEOMODE2; MAP 11.70%; Pooled]
0%
10%
20%
30%
70%
80%
90%
100%
40% 50% 60%</p>
      <p>Average Precision
10.2455/TUKEY_T_TEST.40A773D08F2E0F044438139E14B327C3</p>
      <p>GeoCLEF Monolingual German Task − Tukey T test with "top group" highlighted
FUHTDN5DE
FUHTDN4DE
GEOMODE4
GEOMODE5
GEOMODE1</p>
      <p>GEOMODE6
s
t
n
e
m
i
r
e
p
x
E</p>
      <p>HIMODENE2NA</p>
      <p>FUHTD6DE
HIMODEBASE</p>
      <p>FUHTD3DE
HIMODENE2</p>
      <p>FUHTD2DE
HIMODENE3
GEOMODE2</p>
      <p>GEOMODE3
BERKMODEBASE</p>
      <p>30 100 200
Retrieved Documents (logarithmic scale)
500
1000
GeoCLEF Monolingual German Task Top 5 Participants − Comparison to Median R−Precision by Topic (Topics 51−GC to 75−GC)
hagen [Experiment FUHTDN5DE; R−Prec 26.58%; Pooled]
csusm [Experiment GEOMODE5; R−Prec 22.99%; Pooled]
hildesheim [Experiment HIMODENE2NA; R−Prec 23.41%; Pooled]
cheshire [Experiment BERKMODEBASE; R−Prec 16.36%; Pooled]
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC
Topic Identifier
hildesheim [Experiment HIMODENE2NA; R−Prec 23.41%; Pooled]
s
t
n
e
m
i
r
e
p
x
E
csusm [Experiment GEOMODE5; R−Prec 22.99%; Pooled]
csusm [Experiment GEOMODE4; R−Prec 22.99%; Pooled]
hagen [Experiment FUHTD6DE; R−Prec 22.68%; Pooled]
csusm [Experiment GEOMODE6; R−Prec 22.10%; Pooled]
csusm [Experiment GEOMODE1; R−Prec 22.10%; Pooled]
hagen [Experiment FUHTD2DE; R−Prec 21.66%; Pooled]
hagen [Experiment FUHTD3DE; R−Prec 21.58%; Pooled]
hildesheim [Experiment HIMODEBASE; R−Prec 19.93%; Pooled]
hildesheim [Experiment HIMODENE2; R−Prec 19.48%; Pooled]
hildesheim [Experiment HIMODENE3; R−Prec 18.60%; Pooled]
cheshire [Experiment BERKMODEBASE; R−Prec 16.36%; Pooled]
csusm [Experiment GEOMODE3; R−Prec 14.75%; Pooled]
csusm [Experiment GEOMODE2; R−Prec 14.75%; Pooled]
0%
10%
20%
30%
40%
60%
70%
80%
90%</p>
      <p>100%
50%</p>
      <p>R−Precision</p>
      <p>GeoCLEF Monolingual German Task − Tukey T test with "top group" highlighted
s
t
n
e
m
i
r
e
p
x
E
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
depok</p>
      <p>GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment</p>
      <p>GeoCLEF Bilingual English Task − 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>Average Precision
Precision averages (%) for individual
queries
0%5</p>
      <p>GeoCLEF Bilingual English Task − 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>R−Precision
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
depok
0.0198 Query translation using machine translation. query
0.1716 expansion is done by georeference processing
100%
90%
80%
70%
60%
40%
30%
20%
10%</p>
      <p>GeoCLEF Bilingual English Task − Distribution of the Topics of the Experiment
15
Precision averages (%) for individual
queries
depok</p>
      <sec id="sec-15-1">
        <title>Docs Cutoff Levels Precision at DCL (%)</title>
        <p>0%5</p>
        <p>GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual English Task − Distribution of the Topics of the Experiment
15
t
n
e
m
ir
e
p
xE10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N
depok
GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment
0
10
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
Precision averages (%) for individual
queries</p>
        <p>GeoCLEF Bilingual English Task − 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%
Average Precision
Precision averages (%) for individual
queries
depok
Query translation using machine translation. query
expansion is done by georeference processing and
pseudo relevance feeddback on geo terms
0%5</p>
        <p>GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual English Task − 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%
R−Precision
depok</p>
        <p>GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual English Task − 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%
Average Precision
Query translation using machine translation. query
expansion is done by georeference processing and
common pseudo relevance Feedback
0%5
depok
Precision averages (%) for individual
queries
GeoCLEFBilingualEnglishTask−ComparisontoMedianR−PrecisionbyTopic(Topics51−GCto75−GC)</p>
        <p>UIBITGPPF5</p>
        <p>GeoCLEF Bilingual English Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual English Task − 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%
R−Precision</p>
      </sec>
      <sec id="sec-15-2">
        <title>Priority</title>
      </sec>
      <sec id="sec-15-3">
        <title>Query Construction 25,000 Source Language 762 Topic Fields 352 Pooled</title>
        <p>1</p>
      </sec>
      <sec id="sec-15-4">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-5">
        <title>German</title>
        <p>title, description
true
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
        <p>Recall</p>
        <p>GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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%
Average Precision
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
i
rpe15
x
E
e
h
ftso10
cp
i
o
T
f
o
re 5
b
m
u</p>
        <p>N
Precision averages (%) for individual
queries
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
0%5</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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%
R−Precision</p>
      </sec>
      <sec id="sec-15-6">
        <title>Priority</title>
      </sec>
      <sec id="sec-15-7">
        <title>Query Construction 25,000 Source Language 762 Topic Fields 402 Pooled</title>
        <p>2</p>
      </sec>
      <sec id="sec-15-8">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-9">
        <title>English</title>
        <p>title, description
true</p>
        <p>GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
tfsceop54
h
i
o3
T
f
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%
Average Precision
Precision averages (%) for individual
queries
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
0%5</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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%
R−Precision
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier</p>
      </sec>
      <sec id="sec-15-10">
        <title>Priority</title>
      </sec>
      <sec id="sec-15-11">
        <title>Query Construction 25,000 Source Language 762 Topic Fields 465 Pooled</title>
        <p>3</p>
      </sec>
      <sec id="sec-15-12">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-13">
        <title>Spanish; Castilian</title>
        <p>title, description
true
0%0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
        <p>Recall</p>
        <p>GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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%
Average Precision
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
Baseline Spanish to Portuguese using Powertrans and
searching using TREC2 ranking with Blind Feedback
Precision averages (%) for individual
queries
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
20%
10%
0%5
−0.2
−0.4
−0.6
−0.8</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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%
R−Precision
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier
10
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
csusm
Overall statistics for 25 queries :
Total number of documents over all queries</p>
      </sec>
      <sec id="sec-15-14">
        <title>Retrieved</title>
      </sec>
      <sec id="sec-15-15">
        <title>Relevant</title>
      </sec>
      <sec id="sec-15-16">
        <title>Relevant retrieved</title>
        <p>1</p>
      </sec>
      <sec id="sec-15-17">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-18">
        <title>Spanish; Castilian</title>
        <p>title, description
true
0.0011 Spanish topics, English docs, title &amp; description
0.0408
−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>Average Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
Precision averages (%) for individual
queries
csusm</p>
      </sec>
      <sec id="sec-15-19">
        <title>Docs Cutoff Levels Precision at DCL (%)</title>
        <p>−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>R−Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%
R−Precision
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier
10
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
csusm
Overall statistics for 25 queries :
Total number of documents over all queries</p>
      </sec>
      <sec id="sec-15-20">
        <title>Retrieved</title>
      </sec>
      <sec id="sec-15-21">
        <title>Relevant</title>
      </sec>
      <sec id="sec-15-22">
        <title>Relevant retrieved</title>
        <p>2</p>
      </sec>
      <sec id="sec-15-23">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-24">
        <title>Spanish; Castilian</title>
        <p>title, description
true
0.0010 Spanish topic's title &amp; description with relevance
0.0407 feedback
−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>Average Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
Precision averages (%) for individual
queries
csusm</p>
      </sec>
      <sec id="sec-15-25">
        <title>Docs Cutoff Levels Precision at DCL (%)</title>
        <p>−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>R−Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%
R−Precision
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier
10
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
csusm
Overall statistics for 25 queries :
Total number of documents over all queries</p>
      </sec>
      <sec id="sec-15-26">
        <title>Retrieved</title>
      </sec>
      <sec id="sec-15-27">
        <title>Relevant</title>
      </sec>
      <sec id="sec-15-28">
        <title>Relevant retrieved</title>
        <p>3</p>
      </sec>
      <sec id="sec-15-29">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-30">
        <title>Spanish; Castilian</title>
        <p>title, description, narrative
true
0.0010 Spanish topic's title, description, &amp; narrative
0.0407
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>Average Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
Precision averages (%) for individual
queries
csusm</p>
      </sec>
      <sec id="sec-15-31">
        <title>Docs Cutoff Levels</title>
      </sec>
      <sec id="sec-15-32">
        <title>Precision at DCL (%)</title>
        <p>ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>R−Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
00% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%
R−Precision
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier
10
20
30
40
50
60
70
80
90
100
Average precision (non-interpolated) for all
relevant documents (averaged over queries)
csusm
Overall statistics for 25 queries :
Total number of documents over all queries</p>
      </sec>
      <sec id="sec-15-33">
        <title>Retrieved</title>
      </sec>
      <sec id="sec-15-34">
        <title>Relevant</title>
      </sec>
      <sec id="sec-15-35">
        <title>Relevant retrieved</title>
        <p>4</p>
      </sec>
      <sec id="sec-15-36">
        <title>AUTOMATIC</title>
      </sec>
      <sec id="sec-15-37">
        <title>Spanish; Castilian</title>
        <p>title, description, narrative
true
0.0011 Spanish topic's title, description, &amp; narrative
0.0408 with relevance feedback
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
−1 51−GC 52−GC 53−GC 54−GC 55−GC 56−GC 57−GC 58−GC 59−GC 60−GC 61−GC 62−GC 63−GC 64−GC 65−GC 66−GC 67−GC 68−GC 69−GC 70−GC 71−GC 72−GC 73−GC 74−GC 75−GC</p>
        <p>TopicIdentifier</p>
        <p>GeoCLEF Bilingual Portuguese Task − 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>Average Precision</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
20
t
n
e
m
i
rpe15
x
E
e
h
ftso10
cp
i
o
T
f
o
re 5
b
m
u
N</p>
      </sec>
      <sec id="sec-15-38">
        <title>Interquartile range</title>
      </sec>
      <sec id="sec-15-39">
        <title>Mean</title>
      </sec>
      <sec id="sec-15-40">
        <title>Mean With No Outliers</title>
        <p>Std With No Outliers
51-GC
52-GC
53-GC
54-GC
55-GC
56-GC
57-GC
58-GC
59-GC
60-GC
61-GC
62-GC
63-GC
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
Precision averages (%) for individual
queries
GEOBIESPT4
1
100%
90%
80%
70%
40%
30%
20%
10%
500
1000</p>
        <p>GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment</p>
        <p>GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment</p>
      </sec>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>