<!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 Core Tracks Ad-hoc Bilingual and Monolingual Tasks</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>373</fpage>
      <lpage>414</lpage>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>Introduction
3</p>
      <p>Results for CLEF 2006 Ad-Hoc Tracks
List of Submitted Experiments
7
daedalus
daedalus
daedalus
hummingbird
hummingbird
hummingbird
rsi-jhu
rsi-jhu
unine
unine
unine
alicante
alicante
alicante
alicante
daedalus
daedalus
daedalus
erss-toulouse
erss-toulouse
erss-toulouse
hummingbird
hummingbird
hummingbird
indianstat
indianstat
indianstat
indianstat
rim
rim
rim
rim
rsi-jhu
rsi-jhu
rsi-jhu
unine
unine
unine
alicante
alicante
alicante
alicante
daedalus
daedalus
daedalus
hummingbird
hummingbird
hummingbird
mokk
mokk
rsi-jhu
rsi-jhu
unine
unine
unine
alicante</p>
      <p>AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
MANUAL
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
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
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
yes
yes
yes
yes
yes
no
alicante
alicante
alicante
colesir
colesir
daedalus
daedalus
daedalus
hummingbird
hummingbird
hummingbird
nilc-usp
nilc-usp
nilc-usp
pucrs
rsi-jhu
rsi-jhu
rsi-jhu
saocarlos
saocarlos
saocarlos
u.buffalo
u.buffalo
u.buffalo
u.buffalo
ufrgs-usp
ufrgs-usp
ufrgs-usp
ufrgs-usp
unine
unine
unine
xldb
xldb
xldb
xldb
daedalus
daedalus
celi
celi
celi
celi
celi
celi
celi
celi
celi
celi
celi
celi
depok
depok
depok
depok
depok
depok</p>
      <p>AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
MANUAL
MANUAL
MANUAL
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
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
no
no
yes
yes
no
no
yes
no
yes
no
no
yes
no
no
yes
no
yes
no
no
yes
no
yes
no
no
no
yes
no
no
no
yes
no
no
yes
no
no
no
yes
yes
no
no
yes
no
no
no
no
no
no
no
no
no
yes
no
no
no
no
no
depok
depok
dsv
dsv
dsv
dsv
ltrc
ltrc
ltrc
ltrc
ltrc
ltrc
ltrc
rsi-jhu
rsi-jhu
daedalus
daedalus
daedalus
daedalus
queenmary
rsi-jhu
rsi-jhu
rsi-jhu
rsi-jhu
unine
unine
unine
daedalus
daedalus
daedalus
daedalus
daedalus
daedalus
queenmary</p>
      <p>AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
MANUAL
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
AUTOMATIC
Track Overview Results and Graphs
13
−0.4
−0.6
−0.8
−1
1
0.8
0.6
0.4
0.2
−0.4
−0.6
−0.8
−1
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325</p>
    </sec>
    <sec id="sec-2">
      <title>Topic Identifier</title>
      <p>Ad−Hoc Monolingual Bulgarian track Top 5 Participants − Comparison to Median Mean Average Precision by Topic (Topics 351 to 735)
351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375</p>
    </sec>
    <sec id="sec-3">
      <title>Topic Identifier</title>
      <p>Ad−Hoc Monolingual Bulgarian track − Box Plot of the Topics
UniNEbg2 [MAP 33.14%; Pooled]</p>
      <p>UniNEbg3 [MAP 32.98%; Pooled]
02aplmobgtd4 [MAP 31.98%; Pooled]
02aplmobgtdn4 [MAP 31.48%; Pooled]
s
t
n
e
m
i
r
e
p
x
E</p>
      <p>UniNEbg1 [MAP 31.29%; Pooled]
bgFSbg3S [MAP 30.80%; Pooled]
humBG06tde [MAP 30.47%; Pooled]
bgx011bgFW4FS4 [MAP 29.57%; Pooled]
humBG06t [MAP 26.12%; Pooled]
0%
10%
20%
30%
70%
80%</p>
      <p>Ad−Hoc Monolingual Bulgarian track − Tukey T test with "top group" highlighted
s
t
n
e
m
i
r
e
p
x
E
02aplmobgtdn4
Track Overview</p>
      <p>Results and Graphs
−0.4
−0.6
−0.8
−1
1
0.8
0.6
0.2
−0.4
−0.6
−0.8
−1
Ad−Hoc Monolingual Bulgarian track − Box Plot of the Topics
UniNEbg2 [R−Prec 33.14%; Pooled]
UniNEbg3 [R−Prec 33.00%; Pooled]</p>
      <p>UniNEbg1 [R−Prec 31.76%; Pooled]
s
t
n
e
m
i
r
e
p
x
E
02aplmobgtdn4 [R−Prec 31.02%; Pooled]
02aplmobgtd4 [R−Prec 30.95%; Pooled]
bgFSbg3S [R−Prec 30.50%; Pooled]
bgFSbg2S [R−Prec 30.27%; Pooled]
10% 20% 30% 40% 50% 60% 70% 80% 90% 100%</p>
      <p>R−Precision</p>
      <p>Ad−Hoc Monolingual Bulgarian track − Tukey T test with "top group" highlighted
s
t
n
e
m
i
r
e
p
x
E
02aplmobgtdn4
02aplmobgtd4
0.0837 Automatic Retrieval Feedback using TD, 10 docs and
0.2840 300 terms
0%0%
10%
20%
30%</p>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment</p>
      <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanAveragePrecisionbyTopic(Topics326to350)
Mean Average 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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
41.38
1.36
11.47
2.79
0.51
52.11
0.00
83.89
37.25
3.99
38.39
13.87
0.72
13.23
5.87
0.00
2.87
0.09
0.13
1.11
63.31
9.11
1.33
3.95
1.01</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
15
t
n
e
m
ir
e
xp
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N</p>
      <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics326to350)
0.0842 Automatic Retrieval Feedback using TDN, 5 docs and
0.2834 30 terms
0%0%
10%
20%
30%</p>
      <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment</p>
      <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanAveragePrecisionbyTopic(Topics326to350)
Mean Average 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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
39.60
1.94
12.52
2.54
0.52
50.21
0.00
84.79
37.16
3.91
41.40
14.01
0.46
12.68
5.23
0.00
3.06
0.06
0.14
1.86
63.61
9.92
1.80
5.95
0.99</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
15
t
n
e
m
ir
e
xp
E10
e
h
ft
so
cp
i
o
fT 5
o
r
e
b
m
u
N</p>
      <sec id="sec-3-1">
        <title>UBen2ptTDrf3</title>
      </sec>
      <sec id="sec-3-2">
        <title>UBen2ptTDrf3</title>
        <p>Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
0%5
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
10
t
n
e
irm 8
e
xp
E
the 6
f
so
c
iop 4
T
f
o
r
e
b 2
m
u
N</p>
        <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics326to350)
0.0962 Automatic Retrieval Feedback using TDN, 10 docs and
0.2949 300 terms
0%0%
10%
20%
30%</p>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc 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>
      </sec>
    </sec>
    <sec id="sec-4">
      <title>Mean Average Precision</title>
      <p>Mean Average 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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
41.18
0.38
6.67
12.75
0.78
48.61
0.28
80.49
29.63
0.94
47.05
15.67
0.14
8.76
5.08
0.00
4.38
1.03
0.15
0.97
64.55
15.47
1.42
4.33
1.04</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
irpe15
x
E
e
h
ftso10
cp
i
o
T
f
o
re 5
b
m
u
N</p>
      <sec id="sec-4-1">
        <title>UBen2ptTDNrf2</title>
      </sec>
      <sec id="sec-4-2">
        <title>UBen2ptTDNrf2</title>
        <p>Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
0%5
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
15
t
n
e
m
ir
e
xp
E10
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%</p>
      </sec>
    </sec>
    <sec id="sec-5">
      <title>Exact R−Precision</title>
      <sec id="sec-5-1">
        <title>UBen2ptTDNrf2</title>
      </sec>
      <sec id="sec-5-2">
        <title>UBen2ptTDNrf2</title>
        <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics326to350)
0.0994 Automatic Retrieval Feedback using TDN, 5 docs and
0.2967 30 terms
0%0%
10%
20%
30%</p>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc 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>
      </sec>
    </sec>
    <sec id="sec-6">
      <title>Mean Average Precision</title>
      <p>Mean Average 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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
38.48
0.36
6.62
11.21
0.81
51.41
0.34
80.80
30.99
1.04
46.66
14.91
0.15
8.41
5.72
0.00
5.24
1.54
0.16
1.08
64.47
15.88
1.41
5.70
1.14</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
60%
40%
30%
20%
10%
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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
35.71
2.50
10.00
15.52
3.17
54.39
0.00
76.67
34.88
3.82
46.41
19.23
2.33
15.38
9.76
0.00
12.70
0.00
2.70
3.45
65.00
20.00
7.14
11.82
4.41</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
15
t
n
e
m
ir
e
xp
E10
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%</p>
    </sec>
    <sec id="sec-7">
      <title>Exact R−Precision</title>
      <sec id="sec-7-1">
        <title>UBen2ptTDNrf3</title>
      </sec>
      <sec id="sec-7-2">
        <title>UBen2ptTDNrf3</title>
        <p>unine
Priority</p>
        <p>Query Construction
50,000 Source Language
2,677 Topic Fields
2,289 Pooled
2
AUTOMATIC
English
title, description
false
0.2130 data fusion of DFR, Okapi &amp; LM (QT: promt &amp; free)
0.3917
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
Precision averages (%) for individual
queries
0%0%
10%
20%
30%</p>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
6
t
n
ire5
m
e
xp
E4
e
h
ftcspo3
i
o
f 2
T
o
r
e
b
m1
u
N
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>Mean Average Precision</title>
      <p>Docs Cutoff Levels Precision at DCL (%)
5 docs 55.60
10 docs 51.60
15 docs 48.80
20 docs 46.10
30 docs 42.60
100 docs 26.62
200 docs 16.89
500 docs 8.12
1000 docs 4.58
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
38.77
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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
60.71
51.25
26.00
29.31
0.00
52.63
0.00
73.33
25.58
67.18
51.38
0.00
39.53
11.54
15.85
40.23
55.56
9.09
64.86
0.00
65.00
14.29
12.50
56.36
8.82</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
unine
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)</p>
      <sec id="sec-8-1">
        <title>UniNEBipt1</title>
      </sec>
      <sec id="sec-8-2">
        <title>UniNEBipt1</title>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
8
tn7
e
m
ire6
xp
E
ftscope45
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%</p>
      </sec>
    </sec>
    <sec id="sec-9">
      <title>Exact R−Precision</title>
      <p>unine
0.2077 data fusion of DFR &amp; LM (QT: promt, free &amp; online)
0.4000
0%0%
10%
20%
30%
70%
80%</p>
      <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
6
t
n
ire5
m
e
xp
E4
e
h
ftscop3
i
o
f 2
T
o
r
e
b
m1
u
N
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-10">
      <title>Mean Average Precision</title>
      <sec id="sec-10-1">
        <title>UniNEBipt2</title>
      </sec>
      <sec id="sec-10-2">
        <title>UniNEBipt2</title>
        <p>Precision averages (%) for individual
queries
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8</p>
        <p>Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanAveragePrecisionbyTopic(Topics326to350)
Docs Cutoff Levels Precision at DCL (%)
5 docs 56.00
10 docs 52.80
15 docs 49.60
20 docs 47.60
30 docs 43.20
100 docs 26.56
200 docs 16.95
500 docs 8.30
1000 docs 4.63
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
40.94
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
unine
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)</p>
      </sec>
      <sec id="sec-10-3">
        <title>UniNEBipt2</title>
      </sec>
      <sec id="sec-10-4">
        <title>UniNEBipt2</title>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
6
t
n
ire5
m
e
xp
E4
e
h
ftscop3
i
o
f 2
T
o
r
e
b
m1
u
N
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>Exact R−Precision</title>
      <p>unine
0.2288 data fusion of DFR, LM &amp; Okapi (QT: promt &amp; online)
0.4027
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
Precision averages (%) for individual
queries
0%0%
10%
20%
30%
70%
80%</p>
      <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
      <p>Ad−Hoc Bilingual Portuguese track − 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%</p>
    </sec>
    <sec id="sec-12">
      <title>Mean Average Precision</title>
      <p>Docs Cutoff Levels Precision at DCL (%)
5 docs 56.00
10 docs 51.60
15 docs 49.20
20 docs 46.50
30 docs 42.27
100 docs 26.02
200 docs 16.69
500 docs 8.22
1000 docs 4.63
R-Precision (precision after R document retrieved,
where R = Relevant retrieved)
39.30
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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
64.29
53.75
22.00
8.62
0.00
52.63
24.24
71.67
32.56
69.47
45.86
3.85
49.30
11.54
47.56
41.35
39.68
36.36
64.86
0.00
65.00
17.14
7.14
54.55
10.29</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5
unine
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)</p>
      <sec id="sec-12-1">
        <title>UniNEBipt3</title>
      </sec>
      <sec id="sec-12-2">
        <title>UniNEBipt3</title>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
6
t
n
ire5
m
e
xp
E4
e
h
tfscop3
i
o
f 2
T
o
r
e
b
m1
u
N
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>Exact R−Precision</title>
      <p>xldb
Priority</p>
      <p>Query Construction
43,409 Source Language
2,677 Topic Fields
1,303 Pooled
1
AUTOMATIC
English
title
true
0.0364 Automatic query, 32 QE terms, top20k docs, relaxed
0.2362 QC
0%0%
10%
20%
30%
70%
80%</p>
      <p>Ad−Hoc Bilingual Portuguese 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>
    </sec>
    <sec id="sec-14">
      <title>Mean Average Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-15">
      <title>Mean Average Precision</title>
      <p>Mean Average 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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
27.34
0.26
4.25
0.00
0.00
14.81
0.01
66.82
1.17
0.65
49.92
7.18
0.93
0.02
47.17
0.00
15.12
0.02
0.15
0.03
19.39
20.63
1.23
3.15
0.98</p>
      <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
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
r
e
b 5
m
u
N</p>
      <sec id="sec-15-1">
        <title>XLDBBiRel32qe20k</title>
      </sec>
      <sec id="sec-15-2">
        <title>XLDBBiRel32qe20k</title>
        <p>xldb
Precision averages (%) for individual
queries
Ad−HocBilingualPortuguesetrack−ComparisontoMedianMeanExactR−PrecisionbyTopic(Topics301to325)
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
60%
40%
30%
20%
10%
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
Topic 301
Topic 302
Topic 303
Topic 304
Topic 305
Topic 306
Topic 307
Topic 308
Topic 309
Topic 310
Topic 311
Topic 312
Topic 313
Topic 314
Topic 315
Topic 316
Topic 317
Topic 318
Topic 319
Topic 320
Topic 321
Topic 322
Topic 323
Topic 324
Topic 325
32.14
2.50
12.00
0.00
0.00
24.56
0.00
58.33
4.65
2.29
50.83
11.54
0.93
0.00
51.22
0.00
26.98
0.00
2.70
0.00
32.50
28.57
7.14
5.45
5.88</p>
        <p>Topic 326
Topic 327
Topic 328
Topic 329
Topic 330
Topic 331
Topic 332
Topic 333
Topic 334
Topic 335
Topic 336
Topic 337
Topic 338
Topic 339
Topic 340
Topic 341
Topic 342
Topic 343
Topic 344
Topic 345
Topic 346
Topic 347
Topic 348
Topic 349
Topic 350
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
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-16">
      <title>Exact R−Precision</title>
      <p>Ad−Hoc Bilingual Portuguese track − Distribution of the Topics of the Experiment
15
t
n
e
m
ir
e
xp
E10
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%</p>
    </sec>
    <sec id="sec-17">
      <title>Exact R−Precision</title>
      <sec id="sec-17-1">
        <title>XLDBBiRel32qe20k</title>
      </sec>
      <sec id="sec-17-2">
        <title>XLDBBiRel32qe20k</title>
        <p>xldb
Overall statistics for 50 queries :
Total number of documents over all queries
Retrieved
Relevant
Relevant retrieved
Priority</p>
        <p>Query Construction
41,952 Source Language
2,677 Topic Fields
1,236 Pooled
4
AUTOMATIC
English
title
false
0.0245 Automatic query, 16 QE terms, top10k docs, relaxed
0.2357 QC
0%0%
10%
20%
30%
70%
80%
Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
irpe15
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-18">
      <title>Mean Average Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-19">
      <title>Mean Average Precision</title>
      <sec id="sec-19-1">
        <title>XLDBBiRel16qe10k</title>
      </sec>
      <sec id="sec-19-2">
        <title>XLDBBiRel16qe10k</title>
        <p>10 15 20 30 100 200</p>
        <p>Retrieved Documents (logarithmic scale)
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5</p>
        <p>Ad−Hoc Bilingual Portuguese 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>
      </sec>
    </sec>
    <sec id="sec-20">
      <title>Exact R−Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-21">
      <title>Exact R−Precision</title>
      <p>1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
irpe15
x
E
e
h
ftso10
cp
i
o
T
f
o
re 5
b
m
u
N
Precision averages (%) for individual
queries</p>
      <sec id="sec-21-1">
        <title>XLDBBiRel16qe10k</title>
        <p>xldb
Priority</p>
        <p>Query Construction
42,401 Source Language
2,677 Topic Fields
1,254 Pooled
3
AUTOMATIC
English
title
false
0.0300 Automatic query, 32 QE terms, top10k docs, relaxed
0.2439 QC
100%
90%
80%
70%
30%
20%
10%
0%0%
10%
20%
30%
40% 50% 60%</p>
      </sec>
    </sec>
    <sec id="sec-22">
      <title>Interpolated Recall 70% 80% 90% 100%</title>
      <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
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
r
e
b 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 id="sec-23">
      <title>Mean Average Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-24">
      <title>Mean Average Precision</title>
      <sec id="sec-24-1">
        <title>XLDBBiRel32qe10k</title>
      </sec>
      <sec id="sec-24-2">
        <title>XLDBBiRel32qe10k</title>
        <p>10 15 20 30 100 200</p>
        <p>Retrieved Documents (logarithmic scale)
100%
90%
80%
70%
60%
40%
30%
20%
10%
0%5</p>
        <p>Ad−Hoc Bilingual Portuguese 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>
      </sec>
    </sec>
    <sec id="sec-25">
      <title>Exact R−Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-26">
      <title>Exact R−Precision</title>
      <p>1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
irpe15
x
E
e
h
ftso10
cp
i
o
T
f
o
re 5
b
m
u
N
Precision averages (%) for individual
queries</p>
      <sec id="sec-26-1">
        <title>XLDBBiRel32qe10k</title>
        <p>xldb
Priority</p>
        <p>Query Construction
42,790 Source Language
2,677 Topic Fields
1,275 Pooled
2
AUTOMATIC
English
title
false
0.0377 Automatic query, 16 QE terms, top20k docs, relaxed
0.2434 QC
100%
90%
80%
70%
30%
20%
10%
0%0%
10%
20%
30%
40% 50% 60%</p>
      </sec>
    </sec>
    <sec id="sec-27">
      <title>Interpolated Recall 70% 80% 90% 100%</title>
      <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment
Precision averages (%) for individual
queries
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
1
0.8
0.6
0.4
e 0.2
c
reen 0
ifD−0.2
−0.4
−0.6
−0.8
20
t
n
e
m
irpe15
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 id="sec-28">
      <title>Mean Average Precision</title>
      <p>Ad−Hoc 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>
    </sec>
    <sec id="sec-29">
      <title>Mean Average Precision</title>
      <sec id="sec-29-1">
        <title>XLDBBiRel16qe20k</title>
      </sec>
      <sec id="sec-29-2">
        <title>XLDBBiRel16qe20k</title>
        <p>90%
80%
70%
60%
40%</p>
        <p>Ad−Hoc Bilingual Portuguese track − Box plot of the Topics of the Experiment</p>
        <p>Ad−Hoc Bilingual Portuguese track − Distribution 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</p>
      </sec>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>