<!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 A Results of the TEL@CLEF 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>591</fpage>
      <lpage>632</lpage>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Introduction
3</p>
      <p>Results for CLEF 2009 Ad-hoc TEL@CLEF 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
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>TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
en
en
en
en
en
en
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de
de</p>
      <p>TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
de
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
fr
el
el
el
el</p>
      <p>TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
T
T
T
aeb
celi
celi
celi
celi
celi
AH-TEL-BILI-X2EN-CLEF2009
el
de
de
fr
fr
it
de
fr
de
fr
de
de
fr
fr
zh
zh
zh
de
de
de
fr
fr
de
de
de
de
de
de
fr
fr
de
de
fr
fr
fr
de
fr
de
fr
en</p>
      <p>T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
T
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
chemnitz
en
fr
fr
it
en
fr
en
fr
zh
en
fr
fr
en
en
en
fr
fr
en
en
fr
fr
en
fr
en
fr
de
en
en
it
it
en
de
de
en
de
de
en
en
de
de</p>
      <p>TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
TD
Track Overview Results and Graphs
15</p>
    </sec>
    <sec id="sec-2">
      <title>Topic Identifier</title>
      <p>Ad−Hoc TEL Monolingual English Task Top 5 Participants − Comparison to Median Average Precision by Topic (Topics 726−AH to 750−AH)
1</p>
    </sec>
    <sec id="sec-3">
      <title>Topic Identifier</title>
      <p>s
t
n
e
m
i
r
e
p
x
E
10.2455/TUKEY_T_TEST.A08D93626F6F439C96C3FC146DDD2BBB
s
t
n
e
m
i
r
e
p
x
E
Precision averages (%) for individual
queries</p>
      <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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
N</p>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-4">
      <title>Average Precision</title>
      <sec id="sec-4-1">
        <title>DE_INDEXBL</title>
      </sec>
      <sec id="sec-4-2">
        <title>DE_INDEXBL</title>
        <p>Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
10
t
n
e
irm 8
e
xp
E
the 6
f
so
c
iop 4
T
f
o
rbe 2
m
u
N</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-5">
      <title>R−Precision</title>
      <sec id="sec-5-1">
        <title>DE_INDEXBL</title>
      </sec>
      <sec id="sec-5-2">
        <title>DE_INDEXBL</title>
        <p>0.0747 IR with multiple indexes, ESA and aggregated scores
0.2223
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French Task − Distribution of the Topics of the Experiment
0%5
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-6">
      <title>R−Precision</title>
      <sec id="sec-6-1">
        <title>EN_INDEXALLESA</title>
      </sec>
      <sec id="sec-6-2">
        <title>EN_INDEXALLESA</title>
        <p>0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-7">
      <title>Average Precision</title>
      <sec id="sec-7-1">
        <title>EN_INDEXBL</title>
      </sec>
      <sec id="sec-7-2">
        <title>EN_INDEXBL</title>
        <p>0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-8">
      <title>R−Precision</title>
      <sec id="sec-8-1">
        <title>EN_INDEXBL</title>
      </sec>
      <sec id="sec-8-2">
        <title>EN_INDEXBL</title>
        <p>0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-9">
      <title>Average Precision</title>
      <sec id="sec-9-1">
        <title>TCDDEFRRUN2</title>
      </sec>
      <sec id="sec-9-2">
        <title>TCDDEFRRUN2</title>
        <p>0%5
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-10">
      <title>R−Precision</title>
      <sec id="sec-10-1">
        <title>TCDDEFRRUN2</title>
      </sec>
      <sec id="sec-10-2">
        <title>TCDDEFRRUN2</title>
        <p>0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-11">
      <title>Average Precision</title>
      <sec id="sec-11-1">
        <title>TCDDEFRRUN3</title>
      </sec>
      <sec id="sec-11-2">
        <title>TCDDEFRRUN3</title>
        <p>0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-12">
      <title>R−Precision</title>
      <sec id="sec-12-1">
        <title>TCDDEFRRUN3</title>
      </sec>
      <sec id="sec-12-2">
        <title>TCDDEFRRUN3</title>
        <p>0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-13">
      <title>Average Precision</title>
      <sec id="sec-13-1">
        <title>TCDENFRRUN2</title>
      </sec>
      <sec id="sec-13-2">
        <title>TCDENFRRUN2</title>
        <p>0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-14">
      <title>R−Precision</title>
      <sec id="sec-14-1">
        <title>TCDENFRRUN2</title>
      </sec>
      <sec id="sec-14-2">
        <title>TCDENFRRUN2</title>
        <p>0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-15">
      <title>Average Precision</title>
      <sec id="sec-15-1">
        <title>TCDENFRRUN3</title>
      </sec>
      <sec id="sec-15-2">
        <title>TCDENFRRUN3</title>
        <p>20%
10%
0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-16">
      <title>R−Precision</title>
      <sec id="sec-16-1">
        <title>TCDENFRRUN3</title>
      </sec>
      <sec id="sec-16-2">
        <title>TCDENFRRUN3</title>
        <p>Overall statistics for 50 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
        <p>Query Construction
50,000 Source Language
1,853 Topic Fields
995 Pooled
0.0131 CL-ESA with 169283 dimensions, querying the french
0.1370 collection with german topics
0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
30
t
n
iem25
r
e
p
xE20
e
h
ftso15
cp
i
o
fT10
o
r
e
b
m 5
u
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-17">
      <title>Average Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-18">
      <title>Average Precision</title>
      <sec id="sec-18-1">
        <title>CLESA169283DEINFR</title>
      </sec>
      <sec id="sec-18-2">
        <title>CLESA169283DEINFR</title>
        <p>20%
10%
0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-19">
      <title>R−Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-20">
      <title>R−Precision</title>
      <sec id="sec-20-1">
        <title>CLESA169283DEINFR</title>
      </sec>
      <sec id="sec-20-2">
        <title>CLESA169283DEINFR</title>
        <p>Overall statistics for 50 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
        <p>Query Construction
50,000 Source Language
1,853 Topic Fields
1,152 Pooled
0.0442 CL-ESA with 169283 dimensions, querying the french
0.1552 collection with english topics
0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-21">
      <title>Average Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-22">
      <title>Average Precision</title>
      <sec id="sec-22-1">
        <title>CLESA169283ENINFR</title>
      </sec>
      <sec id="sec-22-2">
        <title>CLESA169283ENINFR</title>
        <p>Docs Cutoff Levels Precision at DCL (%)
5 docs 22.80
10 docs 20.20
15 docs 20.00
20 docs 19.80
30 docs 18.33
100 docs 11.38
200 docs 7.25
500 docs 3.86
1000 docs 2.30
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
18.61
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
R_PRECISION
Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc TEL Bilingual French 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>
      </sec>
    </sec>
    <sec id="sec-23">
      <title>R−Precision</title>
      <sec id="sec-23-1">
        <title>CLESA169283ENINFR</title>
      </sec>
      <sec id="sec-23-2">
        <title>CLESA169283ENINFR</title>
        <p>Overall statistics for 50 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
        <p>Query Construction
50,000 Source Language
1,853 Topic Fields
973 Pooled
0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
−1 701−AH702−AH703−AH704−AH705−AH706−AH707−AH708−AH709−AH710−AH711−AH712−AH713−AH714−AH715−AH716−AH717−AH718−AH719−AH720−AH721−AH722−AH723−AH724−AH725−AH</p>
      </sec>
      <sec id="sec-23-3">
        <title>TopicIdentifier</title>
        <p>Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-24">
      <title>Average Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-25">
      <title>Average Precision</title>
      <sec id="sec-25-1">
        <title>COMBINEDDEINFR</title>
      </sec>
      <sec id="sec-25-2">
        <title>COMBINEDDEINFR</title>
        <p>20%
10%
0%5
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Combined rankings, each computed with a different
topic field, querying the french collection with
german topics
5.88
0.00
0.00
0.00
12.96
21.74
20.59
16.67
15.00
13.73
3.45
10.98
52.50
45.00
20.37
8.33
45.45
0.00
12.90
1.59
31.67
0.00
33.33
23.73
12.36
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−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
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-26">
      <title>R−Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-27">
      <title>R−Precision</title>
      <sec id="sec-27-1">
        <title>COMBINEDDEINFR</title>
      </sec>
      <sec id="sec-27-2">
        <title>COMBINEDDEINFR</title>
        <p>−1 701−AH702−AH703−AH704−AH705−AH706−AH707−AH708−AH709−AH710−AH711−AH712−AH713−AH714−AH715−AH716−AH717−AH718−AH719−AH720−AH721−AH722−AH723−AH724−AH725−AH</p>
      </sec>
      <sec id="sec-27-3">
        <title>TopicIdentifier</title>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianR−PrecisionbyTopic(Topics726−AHto750−AH)
−1 726−AH727−AH728−AH729−AH730−AH731−AH732−AH733−AH734−AH735−AH736−AH737−AH738−AH739−AH740−AH741−AH742−AH743−AH744−AH745−AH746−AH747−AH748−AH749−AH750−AH</p>
      </sec>
      <sec id="sec-27-4">
        <title>TopicIdentifier</title>
        <p>Overall statistics for 50 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
        <p>Query Construction
50,000 Source Language
1,853 Topic Fields
611 Pooled
20%
10%
0%0%
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
6.61
0.00
0.01
2.80
8.03
0.40
7.93
0.02
10.00
3.26
0.48
0.98
18.75
18.93
17.18
2.22
35.58
0.36
4.72
3.77
20.44
0.25
0.00
10.42
1.83
−1 701−AH702−AH703−AH704−AH705−AH706−AH707−AH708−AH709−AH710−AH711−AH712−AH713−AH714−AH715−AH716−AH717−AH718−AH719−AH720−AH721−AH722−AH723−AH724−AH725−AH</p>
      </sec>
      <sec id="sec-27-5">
        <title>TopicIdentifier</title>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics726−AHto750−AH)
−1 726−AH727−AH728−AH729−AH730−AH731−AH732−AH733−AH734−AH735−AH736−AH737−AH738−AH739−AH740−AH741−AH742−AH743−AH744−AH745−AH746−AH747−AH748−AH749−AH750−AH</p>
      </sec>
      <sec id="sec-27-6">
        <title>TopicIdentifier</title>
        <p>Precision averages (%) for individual
queries</p>
        <p>Ad−HocTELBilingualFrenchTask−ComparisontoMedianAveragePrecisionbyTopic(Topics701−AHto725−AH)
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
ce 0.2
reen 0
ifD−0.2
−0.4
−0.6
−0.8
40
ten35
m
i
rpe30
x
E
ftsoe2205
h
cp
i
foT15
o
re10
b
m
u 5
N
0% 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95% 100%</p>
      </sec>
    </sec>
    <sec id="sec-28">
      <title>Average Precision</title>
      <p>Ad−Hoc TEL Bilingual French 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>
    </sec>
    <sec id="sec-29">
      <title>Average Precision</title>
      <sec id="sec-29-1">
        <title>COMBINEDENINFR</title>
      </sec>
      <sec id="sec-29-2">
        <title>COMBINEDENINFR</title>
        <p>80%
70%
60%
500
1000
Ad−Hoc TEL Bilingual French Task − Box plot of the Topics of the Experiment
Combined rankings, each computed with a different
topic field, querying the french collection with
english topics
Interquartile range
Mean
Mean With No Outliers
Std With No Outliers
701-AH
702-AH
703-AH
704-AH
705-AH
706-AH
707-AH
708-AH
709-AH
710-AH
711-AH
712-AH
713-AH
714-AH
715-AH
716-AH
717-AH
718-AH
719-AH
720-AH
721-AH
722-AH
723-AH
724-AH
725-AH</p>
      </sec>
      <sec id="sec-29-3">
        <title>COMBINEDENINFR</title>
      </sec>
      <sec id="sec-29-4">
        <title>COMBINEDENINFR</title>
      </sec>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>