<!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 E 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>429</fpage>
      <lpage>470</lpage>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Introduction
3</p>
      <p>Results for CLEF 2008 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
alivale
alivale
alivale
alivale
alivale
alivale
alivale
alivale
alivale
United States
10.2415/GC-MONO-EN</p>
    </sec>
    <sec id="sec-2">
      <title>CLEF2008.CHESHIRE.BERKGCMOENTD</title>
      <p>United States
10.2415/GC-MONO-EN</p>
    </sec>
    <sec id="sec-3">
      <title>CLEF2008.CHESHIRE.BERKGCMOENTDN</title>
      <p>United States
10.2415/GC-MONO-EN</p>
      <p>CLEF2008.CHESHIRE.BERKGCMOENTDNPIV
United States 10.2415/GC-MONO-EN-CLEF2008.CSUSM.MONEN1
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en</p>
      <p>TDN
TDN
TDN
TDN
TDN
TDN
TD
TDN
TDN
TD
TDN
TDN
TD
TDN
TDN
TD
TDN
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TDN
TDN</p>
    </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>
    </sec>
    <sec id="sec-8">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-9">
      <title>AUTOMATIC</title>
      <p>AUTOMATIC
yes
yes
yes
yes
yes
yes
yes
jaen
jaen
jaen
jaen
jaen
jaen
pittsburgh
pittsburgh
pittsburgh
pittsburgh
valencia
valencia
valencia
valencia
valencia
valencia
xldb
xldb
xldb
xldb
xldb
xldb
xldb
xldb
xldb
xldb
xldb
xldb
10.2415/GC-MONO-DE-CLEF2008.HAGEN.FUHTD20 GC-MONO-DE-CLEF2008
10.2415/GC-MONO-DE</p>
    </sec>
    <sec id="sec-10">
      <title>CLEF2008.HAGEN.FUHTD01M</title>
      <p>10.2415/GC-MONO-DE</p>
    </sec>
    <sec id="sec-11">
      <title>CLEF2008.HAGEN.FUHTD20M</title>
      <p>10.2415/GC-MONO-DE</p>
    </sec>
    <sec id="sec-12">
      <title>CLEF2008.HAGEN.FUHTDN20</title>
      <p>United States
10.2415/GC-MONO-PT</p>
    </sec>
    <sec id="sec-13">
      <title>CLEF2008.CHESHIRE.BERKGCMOPTTD</title>
      <p>United States
10.2415/GC-MONO-PT</p>
    </sec>
    <sec id="sec-14">
      <title>CLEF2008.CHESHIRE.BERKGCMOPTTDN United States 10.2415/GC-MONO-PTCLEF2008.CHESHIRE.BERKGCMOPTTDNPIV</title>
      <p>10.2415/GC-MONO-EN-CLEF2008.JAEN.EXP5
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
en
de
de
de
de
de
de
de
de
en
pt
en
pt</p>
      <p>TDN
TDN
TDN
TD
TDN
TDN
TDN
TD
T
TN
TDN
TDN
TDN
TD
TD
TDN
T
T
T
T
T
T
T
T
T
T
T
T
TD
TDN
TDN
TD
TD
TD
TD
TD
TDN
TD
TDN
TDN</p>
    </sec>
    <sec id="sec-15">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-16">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-17">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-18">
      <title>AUTOMATIC</title>
    </sec>
    <sec id="sec-19">
      <title>AUTOMATIC</title>
      <p>yes
yes
yes
yes
yes
United States 10.2415/GC-MONO-PT-CLEF2008.CSUSM.MONPT1
en
pt
pt
pt
pt
pt
pt
pt
pt
pt
pt
pt
pt
pt
de
de
de
pt
pt
pt
de
en
en
en
en
en
en
en
en
pt
pt
en
en
en
en
en
en
en
en
pt</p>
      <p>TD
T
T
T
T
T
T
T
T
T
T
T
T
T
TD
TDN
TDN
TD
TDN
TDN
TD
TD
TDN
TDN
TD
TDN
TDN
TD
TDN
TD
TDN
TDN
TDN
TD
TD
TDN
TD
TD
TDN
TD
hagen
hagen
hagen
hagen
csusm
Track Overview Results and Graphs
13</p>
      <sec id="sec-19-1">
        <title>Track Overview Results and</title>
        <p>GeoCLEF Monolingual English</p>
        <sec id="sec-19-1-1">
          <title>Task</title>
          <p>Top 5 Participants − Standard
Recall Levels
vs Mean Interpolated
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
−1
Track Overview Results and Graphs
16</p>
        </sec>
      </sec>
      <sec id="sec-19-2">
        <title>Track Overview Results and</title>
        <p>GeoCLEF Monolingual English</p>
        <sec id="sec-19-2-1">
          <title>Task</title>
          <p>Top 5 Participants − Retrieved
documents
vs Mean
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
−1
Track Overview Results and Graphs
20
hagen
hagen
R_PRECISION</p>
          <p>GeoCLEF Bilingual German Task − Distribution of the Topics of the Experiment
5
t
n
e
ie4
m
r
xp
E
tfh3
e
so
c
ip2
o
T
f
o
r
e
b1
m
u
N
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
hagen
GeoCLEF Bilingual German Task − Distribution of the Topics of the Experiment
0%5
hagen
R_PRECISION
Precision averages (%) for individual
queries</p>
          <p>GeoCLEF Bilingual German Task − Distribution of the Topics of the Experiment
6
t
iren5
m
e
xp
E4
e
h
ftscop3
i
o
f2
T
o
r
e
bu1
m
N
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
hagen</p>
          <p>GeoCLEF Bilingual German Task − Box plot of the Topics of the Experiment
GeoCLEF Bilingual German Task − Distribution of the Topics of the Experiment
0%5
hagen
Precision averages (%) for individual
queries
GeoCLEFBilngualGermanTask−ComparisontoMedianR−PrecisionbyTopic(Topics100−GCto99−GC
FUHPTGTDN20</p>
          <p>GeoCLEF Bilingual German Task − Box plot of the Topics of the Experiment</p>
          <p>GeoCLEF Bilingual German 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
1
0.8
0.6
0.4
0.2
hagen</p>
          <p>GeoCLEF Bilingual German Task − Box plot of the Topics of the Experiment
GeoCLEF Bilingual German 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
0%5
hagen
Precision averages (%) for individual
queries</p>
          <p>GeoCLEF Bilingual German Task − Box plot of the Topics of the Experiment</p>
          <p>GeoCLEF Bilingual German 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
1
0.8
0.6
0.4
0.2
Priority</p>
          <p>Query Construction
25,000 Source Language
1,245 Topic Fields
894 Pooled
5
AUTOMATIC
English
title, description, narrative
true</p>
          <p>GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
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
Precision averages (%) for individual
queries
BERKBIENPTTDNPIV
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC</p>
          <p>GeoCLEF Bilingual Portuguese Task − Retrieved documents vs Mean Precision</p>
          <p>BERKBIENPTTDNPIV
Precision averages (%) for individual
queries
0%5
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
Bilingual English to Portuguese using TREC2 with
Blind Feedback merged with OKAPI on title and
description and Narrative</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%</p>
          <p>R−Precision
1
0.8
0.6
0.4
0.2
10
t
n
e
irm8
e
xp
E
the 6
f
so
c
iop 4
T
f
o
rbe 2
m
u</p>
          <p>N
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
Priority</p>
          <p>Query Construction
25,000 Source Language
1,245 Topic Fields
679 Pooled
1
AUTOMATIC
German
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
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
Precision averages (%) for individual
queries
BERKGCBIDEPTTD
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
Docs Cutoff Levels Precision at DCL (%)
5 docs 19.20
10 docs 20.00
15 docs 19.20
20 docs 18.60
30 docs 17.20
100 docs 13.72
200 docs 9.58
500 docs 4.88
1000 docs 2.72
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
16.05
100%
90%
80%
70%
60%
0%5
Precision averages (%) for individual
queries</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%</p>
          <p>R−Precision
1
0.8
0.6
0.4
0.2
15
t
n
e
m
ir
e
p
xE10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u</p>
          <p>N
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
Priority</p>
          <p>Query Construction
25,000 Source Language
1,245 Topic Fields
708 Pooled
2
AUTOMATIC
German
title, description, narrative
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
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
Precision averages (%) for individual
queries
BERKGCBIDEPTTDN
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC</p>
          <p>GeoCLEF Bilingual Portuguese Task − Retrieved documents vs Mean Precision</p>
          <p>BERKGCBIDEPTTDN
Precision averages (%) for individual
queries
20%
10%
0%5
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
Bilingual German to Portuguese using TREC2 with
Blind Feedback on title and description and
narrative</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%</p>
          <p>R−Precision
1
0.8
0.6
0.4
0.2
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
e
p
xE10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u</p>
          <p>N
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
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
1,245 Topic Fields
716 Pooled
6
AUTOMATIC
English
title, description, narrative
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
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
GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
e
p
xE10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u
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
BERKGCBIDEPTTDNPIV
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC</p>
          <p>GeoCLEF Bilingual Portuguese Task − Retrieved documents vs Mean Precision</p>
          <p>BERKGCBIDEPTTDNPIV
Precision averages (%) for individual
queries
20%
10%
0%5
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
Bilingual German to Portuguese using TREC2 with
Blind Feedback merged with OKAPI on title and
description and narrative</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%</p>
          <p>R−Precision
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
e
p
xE10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u</p>
          <p>N
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
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
1,245 Topic Fields
818 Pooled
3
AUTOMATIC
English
title, description
true</p>
          <p>GeoCLEF Bilingual Portuguese Task − Standard Recall Levels vs Mean Interpolated Precision
BERKGCBIENPTTD
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
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
GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
e
p
xE10
e
h
tf
so
cp
i
o
fT 5
o
r
e
b
m
u
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
BERKGCBIENPTTD
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
Docs Cutoff Levels Precision at DCL (%)
5 docs 24.00
10 docs 24.40
15 docs 22.93
20 docs 22.00
30 docs 21.47
100 docs 17.12
200 docs 12.06
500 docs 5.86
1000 docs 3.27
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
20.31
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
21.25
0.00
15.00
25.00
0.00
89.13
0.00
33.33
5.00
7.14
46.67
0.00
Precision averages (%) for individual
queries
GeoCLEFBilngualPortugueseTask−ComparisontoMedianR−PrecisionbyTopic(Topics100−GCto99−GC
BERKGCBIENPTTD</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
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
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
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
1,245 Topic Fields
844 Pooled
4
AUTOMATIC
English
title, description, narrative
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
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
GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
15.47
0.18
2.34
46.31
0.03
88.20
0.00
21.29
6.22
11.65
36.55
0.01
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
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
BERKGCBIENPTTDN
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC</p>
          <p>GeoCLEF Bilingual Portuguese Task − Retrieved documents vs Mean Precision</p>
          <p>BERKGCBIENPTTDN
Precision averages (%) for individual
queries
BERKGCBIENPTTDN
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
GeoCLEF Bilingual Portuguese Task − Box plot of the Topics of the Experiment
Bilingual English to Portuguese using TREC2 with
Blind Feedback on title and description and
Narrative
21.25
0.00
7.50
50.00
0.00
89.13
0.00
16.67
12.50
19.64
50.00
0.00
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
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
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
e
xp
E
the 6
f
so
c
iop 4
T
f
o
rbe 2
m
u</p>
          <p>N
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
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
1,245 Topic Fields
275 Pooled
1
AUTOMATIC
English
title, description
true
0.0003 English topics Portuguese docs
0.0213
20%
10%
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
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
GeoCLEF Bilingual Portuguese Task − Distribution of the Topics of the Experiment
0.03
0.00
0.11
0.00
0.43
0.00
0.00
0.00
0.76
0.45
1.11
0.00
1
0.8
0.6
0.4
0.2
ce
reen 0
if
D
−0.2
−0.4
−0.6
−0.8
25
t
n
e
irm20
e
xp
E
the15
f
so
c
iop10
T
f
o
rbe 5
m
u
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
−1 10 −GC 76−GC 7 −GC 78−GC 79−GC 80−GC 81−GC 82−GC 83−GC 84−GC 85−GC 86−GC TopicIdentifier 8 −GC 89−GC 90−GC 91−GC 92−GC 93−GC 94−GC 95−GC 96−GC 97−GC 98−GC 9 −GC
87−GC
Docs Cutoff Levels Precision at DCL (%)
5 docs 3.20
10 docs 3.60
15 docs 3.73
20 docs 3.20
30 docs 3.07
100 docs 3.36
200 docs 2.98
500 docs 1.89
1000 docs 1.10
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
100%
90%
80%
70%
60%
Interquartile range
Mean
Mean With No Outliers
Std With No Outliers
100-GC
76-GC
77-GC
78-GC
79-GC
80-GC
81-GC
82-GC
83-GC
84-GC
85-GC
86-GC
87-GC
EN2PT1</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
1
25</p>
        </sec>
      </sec>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          0.0025 Bilingual German to
          <article-title>Portuguese using TREC2 with 0.1441 Blind Feedback on title and description 0.0188 Bilingual English to Portuguese using TREC2 with 0.1811 Blind Feedback on title and description</article-title>
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>