Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Comment: Migrated to Confluence 5.3

...

The 1.5.0 SourceForge models must be fully compatible with the 1.5.3
release. In this test all the English models are tested for compatibility
on the English 300k sentences Leipzig Corpus (Which file to download??). It is tested that
the output produced with the same model by both versions has the same md5 hash.

Component

Model

Perf 1.5.2

Perf 1.5.3

Tester

Passed

Comment

Sentence Detector

en-sent.bin

44870.8 sent/s

42733.8 sent/s

William

yes

 

Tokenizer

en-token.bin

2824.2 sent/s

2833.3 sent/s

William

yes

 

Name Finder

en-ner-person.bin

781.3 sent/s

761.6 sent/s

William

yes

 

POS Tagger

en-pos-maxent.bin

773.3 sent/s

816.2 sent/s

William

yes

 

POS Tagger

en-pos-perceptron.bin

 

1138.6 sent/s

1117.1 sent/s  

William

  yes

 

Chunker

en-chunker.bin

 

183.7 sent/s

181.1 sent/s  

William

  yes

 

Parser

en-parser-chunking.bin

 

16.0 sent/s

16.3 sent/s  

William

  yes

 

Note: Test was done on Hardware running Operational System
and Java Java VersionMacBook Pro 15", 2 GHz Core i7, 16GB Ram, 500GB HD running OS X 10.7.5
and Java 1.5.0_30. The performance varies because light weight tasks have been performed in the background while testing.

...

To pass the test the event hash and the model output must be identical.

Component

Model

Training Time 1.5.2

Training Time 1.5.3

Tester

Passed

Comment

Sentence Detector

en-sent.bin

 

 

Jörn

  yes

 

Tokenizer

en-token.bin  

 

Jörn

  yes

 

POS Tagger

en-pos-maxent.bin

 

 

Jörn

  yes

 

POS Tagger

en-pos-perceptron.bin  

 

Jörn

  yes

 

Parser

en-parser-chunking.bin

 

 

Jörn

 

yes

Tested on 10k sentences  

Note: Time was measured with the time command, the value is the "real" time value.

...

 

Component

Data

Tester

Tagging Perf 1.5.2

Tagging Perf 1.5.3

Comment

Sentence Detector

 

 

 

 

 

Tokenizer

 

 

 

 

Name Finder

CONLL 2002 Dutch Person ned.testa

  jkosin

Precision: 0.7552941176470588
Recall: 0.4566145092460882
F-Measure: 0.5691489361702128

 

 

Precision: 0.7552941176470588
Recall: 0.4566145092460882
F-Measure: 0.5691489361702128

 

Name Finder

CONLL 2002 Dutch Person ned.testb

  jkosin

Precision: 0.8505025125628141
Recall: 0.6165755919854281
F-Measure: 0.7148891235480465

Precision: 0.8505025125628141
Recall: 0.6165755919854281
F-Measure: 0.7148891235480465  

 

Name Finder

CONLL 2002 Dutch Organization ned.testa

  jkosin

Precision: 0.8561872909698997
Recall: 0.37317784256559766
F-Measure: 0.5197969543147207

Precision: 0.8561872909698997
Recall: 0.37317784256559766
F-Measure: 0.5197969543147207  

 

Name Finder

CONLL 2002 Dutch Organization ned.testb

  jkosin

Precision: 0.7830374753451677
Recall: 0.4501133786848073
F-Measure: 0.5716342692584593

  Precision: 0.7830374753451677
Recall: 0.4501133786848073
F-Measure: 0.5716342692584593

 

Name Finder

CONLL 2002 Dutch Location ned.testa

  jkosin

Precision: 0.8458333333333333
Recall: 0.42379958246346555
F-Measure: 0.564673157162726

 

 

Name Finder

CONLL 2002 Dutch Location ned.testb

 

Precision: 0.8816326530612245 8458333333333333
Recall: 0.5581395348837209 42379958246346555
F-Measure: 0.6835443037974683  564673157162726

 

Name Finder

CONLL 2002 Dutch Misc Location ned.testa testb

  jkosin

Precision: 0.8354114713216958 8816326530612245
Recall: 0.44786096256684493 5581395348837209
F-Measure: 0.5831157528285466 6835443037974683

Precision: 0.8816326530612245
Recall: 0.5581395348837209
F-Measure: 0.6835443037974683  

 

Name Finder

CONLL 2002 Dutch Misc ned.testb testa

  jkosin

Precision: 0.8264984227129337 8354114713216958
Recall: 0.44144903117101936 44786096256684493
F-Measure: 0.5755079626578803

 

 

Name Finder

CONLL 2002 Combined ned.testa

 5831157528285466

Precision: 0.6509695290858726 8354114713216958
Recall: 0.628822629969419 44786096256684493
F-Measure: 0.6397044526540929 5831157528285466

 

1000 iterations

Name Finder

CONLL 2002 Dutch Combined Misc ned.testb

  jkosin

Precision: 0.6869929337869668 8264984227129337
Recall: 0.6660746003552398 44144903117101936
F-Measure: 0.6763720690543674

 

1000 iterations

Name Finder

CONLL 2002 Spanish Person esp.testa

 5755079626578803

Precision: 0.9010695187165776 8264984227129337
Recall: 0.5515548281505729 44144903117101936
F-Measure: 0.684263959390863  5755079626578803

 

Name Finder

CONLL 2002 Spanish Person esp.testb Combined ned.testa

jkosin  

Precision: 0.9195205479452054 6509695290858726
Recall: 0.7306122448979592 628822629969419
F-Measure: 0.8142532221379833

 

 

6397044526540929

Precision: 0.664424218440839
Recall: 0.6418195718654435
F-Measure: 0.6529263076025666

1000 iterations
OPENNLP-417

Name Name Finder

CONLL 2002 Spanish Organization esp.testa Dutch Combined ned.testb

jkosin  

Precision: 0.8288942695722357 6869929337869668
Recall: 0.6041176470588235 6660746003552398
F-Measure: 0.6988771691051379

 

 

Name Finder

CONLL 2002 Spanish Organization esp.testb

 6763720690543674

Precision: 0.8036277602523659 7006019366657943
Recall: 0.7278571428571429 679269221009896
F-Measure: 0.7638680659670164 6897706776603968

 

  1000 iterations
OPENNLP-417

Name Finder

CONLL 2002 Spanish Location Person esp.testa

  jkosin

Precision: 0.7743016759776536 9010695187165776
Recall: 0.7042682926829268 5515548281505729
F-Measure: 0.7376263970196913

 

 

Name Finder

CONLL 2002 Spanish Location esp.testb

 

684263959390863

Precision: 0.8301886792452831 9010695187165776
Recall: 0.5682656826568265 5515548281505729
F-Measure: 0.6746987951807228  684263959390863

 

Name Finder

CONLL 2002 Spanish Misc Person esp.testa testb

  jkosin

Precision: 0.6492890995260664 9195205479452054
Recall: 0.30786516853932583 7306122448979592
F-Measure: 0.4176829268292683

 

 

8142532221379833

Precision: 0.9195205479452054
Recall: 0.7306122448979592
F-Measure: 0.8142532221379833

 

Name Finder

CONLL 2002 Spanish Misc Organization esp.testb testa

  jkosin

Precision: 0.686046511627907 8288942695722357
Recall: 0.3480825958702065 6041176470588235
F-Measure: 0.461839530332681

 

 

Name Finder

CONLL 2002 Spanish Combined esp.testa

 6988771691051379

Precision: 0.7005423249233671 8288942695722357
Recall: 0.6828315329809239 6041176470588235
F-Measure: 0.6915735567970205 6988771691051379

  1000 iterations

Name Finder

CONLL 2002 Spanish Combined Organization esp.testb

  jkosin

Precision: 0.756635931824532 8036277602523659
Recall: 0.7611017425519955 7278571428571429
F-Measure: 0.7588622670589884

 

7638680659670164

Precision: 0.8036277602523659
Recall: 0.7278571428571429
F-Measure: 0.7638680659670164

  1000 iterations

Name Finder

CONLL 2003 English Person eng2002 Spanish Location esp.testa

jkosin

Precision: 0.9523195876288659 7743016759776536
Recall: 0.8023887079261672 7042682926829268
F-Measure: 0.8709487330583382 7376263970196913

Precision: 0.95231958762886597743016759776536
Recall: 0.80238870792616727042682926829268
F-Measure: 0.8709487330583382 7376263970196913

 

Name Finder

CONLL 2003 English Person eng2002 Spanish Location esp.testb

jkosin

Precision: 0.9391727493917275 8301886792452831
Recall: 0.7161410018552876 5682656826568265
F-Measure: 0.8126315789473685 6746987951807228

Precision: 0.93917274939172758301886792452831
Recall: 0.71614100185528765682656826568265
F-Measure: 0.8126315789473685 6746987951807228

 

Name Finder

CONLL 2003 English Organization eng2002 Spanish Misc esp.testa

jkosin

Precision: 0.8768046198267565 6492890995260664
Recall: 0.6793437733035048 30786516853932583
F-Measure: 0.7655462184873949 4176829268292683

Precision: 0.87680461982675656492890995260664
Recall: 0.679343773303504830786516853932583
F-Measure: 0.7655462184873949 4176829268292683

 

Name Finder

CONLL 2003 English Organization eng2002 Spanish Misc esp.testb

jkosin

Precision: 0.8435980551053485 686046511627907
Recall: 0.6267308850090307 3480825958702065
F-Measure: 0.7191709844559586 461839530332681

Precision: 0.8435980551053485686046511627907
Recall: 0.62673088500903073480825958702065
F-Measure: 0.7191709844559586 461839530332681

 

Name Finder

CONLL 2003 English Location eng2002 Spanish Combined esp.testa

jkosin

Precision: 0.9361421988150099 7005423249233671
Recall: 0.7740881872618399 6828315329809239
F-Measure: 0.8474374255065554 6915735567970205

Precision: 0.93614219881500997047866069323273
Recall: 0.77408818726183996869685129855205
F-Measure: 0.8474374255065554 6957635009310986

1000 iterations
OPENNLP-417  

Name Finder

CONLL 2003 English Location eng2002 Spanish Combined esp.testb

jkosin

Precision: 0.9206349206349206 756635931824532
Recall: 0.7302158273381295 7611017425519955
F-Measure: 0.8144433299899699 7588622670589884

Precision: 0.92063492063492067588711930706902
Recall: 0.73021582733812957633501967397415
F-Measure: 0.8144433299899699 7611041053664006

1000 iterations
OPENNLP-417  

Name Finder

CONLL 2003 English Misc Person eng.testa

jkosin

Precision: 0.9027982326951399 9523195876288659
Recall: 0.6648590021691974 8023887079261672
F-Measure: 0.7657713928794503 8709487330583382

Precision: 0.90279823269513999523195876288659
Recall: 0.66485900216919748023887079261672
F-Measure: 0.7657713928794503 8709487330583382

 

Name Finder

CONLL 2003 English Misc Person eng.testb

jkosin

Precision: 0.8592436974789915 9391727493917275
Recall: 0.5826210826210826 7161410018552876
F-Measure: 0.6943972835314092 8126315789473685

Precision: 0.85924369747899159391727493917275
Recall: 0.58262108262108267161410018552876
F-Measure: 0.6943972835314092 8126315789473685

 

Name Finder

CONLL 2003 English Combined Organization eng.testa

jkosin

Precision: 0.861812521618817 8768046198267565
Recall: 0.8386065297879501 6793437733035048
F-Measure: 0.8500511770726714 7655462184873949

Precision: 0.86406087858872368768046198267565
Recall: 0.84079434533826996793437733035048
F-Measure: 0.8522688502217672 7655462184873949

1000 iterations  

Name Finder

CONLL 2003 English Combined Organization eng.testb

jkosin

Precision: 0.8041311831853597 8435980551053485
Recall: 0.7857648725212465 6267308850090307
F-Measure: 0.7948419450165667 7191709844559586

Precision: 0.80648668236999458435980551053485
Recall: 0.78806657223796046267308850090307
F-Measure: 0.7971702337243664 7191709844559586

1000 iterations  

Name Finder

CONLL 2003 German Person deuEnglish Location eng.testa

  jkosin

Precision: 0.9132653061224489 9361421988150099
Recall: 0.25553176302640973 7740881872618399
F-Measure: 0.3993307306190742

 

Name Finder

CONLL 2003 German Person deu.testb

8474374255065554

Precision: 0.9361421988150099
Recall: 0.7740881872618399
F-Measure: 0.8474374255065554

 

Name Finder

CONLL 2003 English Location eng.testb

jkosin  

Precision: 0.8732106339468303 9206349206349206
Recall: 0.3573221757322176 7302158273381295
F-Measure: 0.507125890736342

 

 

Name Finder

CONLL 2003 German Organization deu.testa

 8144433299899699

Precision: 0.8407224958949097 9206349206349206
Recall: 0.4125705076551168 7302158273381295
F-Measure: 0.5535135135135135 8144433299899699

 

 

Name Finder

CONLL 2003 German Organization deu.testb English Misc eng.testa

jkosin  

Precision: 0.8014705882352942 9027982326951399
Recall: 0.4230271668822768 6648590021691974
F-Measure: 0.5537679932260795

 

 

Name Finder

CONLL 2003 German Location deu.testa

 

7657713928794503

Precision: 0.7816326530612245 9027982326951399
Recall: 0.32430143945808637 6648590021691974
F-Measure: 0.45840813883901854
 7657713928794503

 

Name Finder

CONLL 2003 German Location deuEnglish Misc eng.testb

  jkosin

Precision: 0.8033826638477801 8592436974789915
Recall: 0.3671497584541063 5826210826210826
F-Measure: 0.5039787798408487

 

 

6943972835314092

Precision: 0.8592436974789915
Recall: 0.5826210826210826
F-Measure: 0.6943972835314092

 

Name Finder

CONLL 2003 German Misc deuEnglish Combined eng.testa

  jkosin

Precision: 0.7055555555555556 861812521618817
Recall: 0.12574257425742574 8386065297879501
F-Measure: 0.21344537815126052

 

 

Name Finder

CONLL 2003 German Misc deu.testb

 8500511770726714

Precision: 0.6601307189542484 8640608785887236
Recall: 0.15074626865671642 8407943453382699
F-Measure: 0.2454434993924666 8522688502217672

 

  1000 iterations
OPENNLP-417

Name Finder

CONLL 2003 German Combined deu.testa  English Combined eng.testb

jkosin

Precision: 0.8041311831853597
Recall: 0.7857648725212465
F-Measure: 0.7948419450165667

Precision: 0.7718859429714857 8064866823699945
Recall: 0.319263397475688 7880665722379604
F-Measure: 0.4516978922716628 7971702337243664

 

  1000 iterations
OPENNLP-417

Name Finder

CONLL 2003 German Combined Person deu.testb testa

  jkosin

Precision: 0.7467566165023353 9132653061224489
Recall: 0.3917778382793357 25553176302640973
F-Measure: 0.5139285714285715

 

 

POS Tagger

CONLL 2006 Danish

 

3993307306190742

Precision: 0.9132653061224489
Recall: 0.25553176302640973
F-Measure Accuracy: 0.9511278195488722 3993307306190742

  

Name Finder

POS Tagger

CONLL 2006 Dutch

 

CONLL 2003 German Person deu.testb

jkosin

Precision Accuracy: 0.9324977618621307

 

 

POS Tagger

CONLL 2006 Portuguese

 

Accuracy8732106339468303
Recall: 0.9659110277825124

 

 

POS Tagger

CONLL 2006 Swedish

 

Accuracy: 0.9275106082036775

 

 

3573221757322176
F-Measure: 0.507125890736342

Precision: 0.8732106339468303
Recall: 0.3573221757322176
F-Measure: 0.507125890736342

 

Name Finder

CONLL 2003 German Organization deu.testa

jkosin

Chunker

CONLL 2000

William

Precision: 0.9257575757575758 8407224958949097
Recall: 0.9221868187154117 4125705076551168
F-Measure: 0.9239687473746113

 

 

5535135135135135

Precision: 0.8407224958949097
Recall: 0.4125705076551168
F-Measure: 0.5535135135135135

 

Name Finder

CONLL 2003 German Organization deu.testb

jkosin

Precision: 0.8014705882352942
Recall: 0.4230271668822768

Chunker

Arvores Deitadas
(10-fold cross-validation)

William

Precision: 0.9403445830378374
Recall: 0.9373141775994345
F-Measure:  00.9388269348910339

 

 

Test UIMA Integration

The test ensures that the Analysis Engine can run and not not
crash trough simple runtime time code errors. We need to add
more sophisticated testing with the next releases.

Analysis Engine

Tester

Passed

Comment

Sentence Detector

 

 

 

Sentence Detector Trainer

 

 

 

Tokenizer ME

 

 

 

Tokenizer Trainer

 

 

 

Name Finder

 

 

 

Name Finder Trainer

 

 

 

Chunker

 

 

 

Chunker Trainer

 

 

 

POS Tagger

 

 

 

POS Tagger Trainer

 

 

 

Parser

 

 

 

createPear.sh

 

 

 

Sample PEAR

 

 

 

Distribution Review

Please ensure that the listed files below are included in the distributions
and are in a good state.

...

Package

...

File or Test

...

Tester

...

Passed

...

Comment

...

Binary

...

LICENSE

...

 

...

 

...

AL 2.0 and BSD for JWNL

...

Binary

...

NOTICE

...

 

...

 

...

standard notice, dates are correct. JWNL is mentioned

...

Binary

...

README

...

 

...

 

...

File was reviewed on the dev list.

...

Binary

...

RELEASE_NOTES.html

...

 

...

 

...

issue list is generated correctly

...

Binary

...

Test signatures: .md5, .sha1, .asc

...

 

...

 

...

rc4

...

Binary

...

JIRA issue list created

...

 

...

 

...

 

...

Binary

...

Contains maxent, tools, uima and jwnl jars

...

 

...

 

...

 

...

Source

...

LICENSE

...

 

...

 

...

standard AL 2.0 file

...

Source

...

NOTICE

...

 

...

 

...

standard notice, dates are correct

...

Source

...

Test signatures: .md5, .sha1, .asc

...

 

...

 

...

rc4

...

Source

...

Can build from source?

...

 

...

 

...

5537679932260795

Precision: 0.8014705882352942
Recall: 0.4230271668822768
F-Measure: 0.5537679932260795

 

Name Finder

CONLL 2003 German Location deu.testa

jkosin

Precision: 0.7816326530612245
Recall: 0.32430143945808637
F-Measure: 0.45840813883901854

Precision: 0.7816326530612245
Recall: 0.32430143945808637
F-Measure: 0.45840813883901854

 

Name Finder

CONLL 2003 German Location deu.testb

jkosin

Precision: 0.8033826638477801
Recall: 0.3671497584541063
F-Measure: 0.5039787798408487

Precision: 0.8033826638477801
Recall: 0.3671497584541063
F-Measure: 0.5039787798408487

 

Name Finder

CONLL 2003 German Misc deu.testa

jkosin

Precision: 0.7055555555555556
Recall: 0.12574257425742574
F-Measure: 0.21344537815126052

Precision: 0.7055555555555556
Recall: 0.12574257425742574
F-Measure: 0.21344537815126052

 

Name Finder

CONLL 2003 German Misc deu.testb

jkosin

Precision: 0.6601307189542484
Recall: 0.15074626865671642
F-Measure: 0.2454434993924666

Precision: 0.6601307189542484
Recall: 0.15074626865671642
F-Measure: 0.2454434993924666

 

Name Finder

CONLL 2003 German Combined deu.testa

jkosin

Precision: 0.7718859429714857
Recall: 0.319263397475688
F-Measure: 0.4516978922716628

Precision: 0.7783891945972986
Recall: 0.32195323815435545
F-Measure: 0.45550351288056207

OPENNLP-417

Name Finder

CONLL 2003 German Combined deu.testb

jkosin

Precision: 0.7467566165023353
Recall: 0.3917778382793357
F-Measure: 0.5139285714285715

Precision: 0.749351323300467
Recall: 0.3931391233324258
F-Measure: 0.5157142857142857

OPENNLP-417

POS Tagger

CONLL 2006 Danish

Jörn / ?

Accuracy: 0.9511278195488722

Accuracy: 0.9512987012987013

Jörn: Same result as other tester

POS Tagger

CONLL 2006 Dutch

Jörn

Accuracy: 0.9324977618621307

Accuracy: 0.9324977618621307

 

POS Tagger

CONLL 2006 Portuguese

Jörn / ?

Accuracy: 0.9659110277825124

Accuracy: 0.9659110277825124

Jörn: Same result as other tester

POS Tagger

CONLL 2006 Swedish

Jörn

Accuracy: 0.9275106082036775

Accuracy: 0.9275106082036775

 

Chunker

CONLL 2000

William

Precision: 0.9257575757575758
Recall: 0.9221868187154117
F-Measure: 0.9239687473746113

Precision: 0.9257575757575758
Recall: 0.9221868187154117
F-Measure: 0.9239687473746113

 

Sentence Detector

Arvores Deitadas
(Floresta Virgem)
(10-fold cross-validation)

William

 

Precision: 0.9891491491491492
Recall: 0.9894066523820013
F-Measure: 0.9892778840089301

PERCEPTRON Cutoff 0
1.5.2 works poorly because
we didn't have configurable EOS

Tokenizer

Arvores Deitadas
(Floresta Virgem)
(10-fold cross-validation)

William

 

Precision: 0.9995231988260895
Recall: 0.9994542652270997
F-Measure: 0.9994887308380267

PERCEPTRON Cutoff 0
alphaNumOpt

Chunker

Arvores Deitadas
(10-fold cross-validation)

William

Precision: 0.9404684925220583
Recall: 0.9374181341871635
F-Measure: 0.9389408359191154

Precision: 0.9562405864042575
Recall: 0.9582419351592844
F-Measure: 0.9572402147035765

OPENNLP-541, OPENNLP-423

Test UIMA Integration

The test ensures that the Analysis Engine can run and not not
crash trough simple runtime time code errors. We need to add
more sophisticated testing with the next releases.

Analysis Engine

Tester

Passed

Comment

Sentence Detector

 

 

 

Sentence Detector Trainer

 

 

 

Tokenizer ME

 

 

 

Tokenizer Trainer

 

 

 

Name Finder

 

 

 

Name Finder Trainer

 

 

 

Chunker

 

 

 

Chunker Trainer

 

 

 

POS Tagger

 

 

 

POS Tagger Trainer

 

 

 

Parser

 

 

 

createPear.sh

Jörn

yes

 

Sample PEAR

Jörn

yes

 

Distribution Review

Please ensure that the listed files below are included in the distributions
and are in a good state.

Package

File or Test

Tester

Passed

Comment

Binary

LICENSE

Jörn

Yes

AL 2.0 and BSD for JWNL

Binary

NOTICE

Jörn

Yes

standard notice, dates are correct. JWNL is mentioned

Binary

README

Jörn

Yes

 

Binary

RELEASE_NOTES.html

Jörn

Yes

 

Binary

Test signatures: .md5, .sha1, .asc

Jörn

Yes

tested for rc3

Binary

JIRA issue list created

William

Yes

Minor issue: the project.version was not filled.

Binary

Contains maxent, tools, uima and jwnl jars

Jörn

Yes

 

Source

LICENSE

Jörn

Yes

standard AL 2.0 file

Source

NOTICE

Jörn

Yes

standard notice, dates are correct

Source

Test signatures: .md5, .sha1, .asc

Jörn

 

tested for rc3

Source

Can build from source?

Jörn

Yes

Test should be done without jwnl and opennlp in local m2 repo.

Notes about testing

Compatibility tests

The following commands can be used to reproduce the compatibility tests with Leipzig corpus.

Code Block

# Corpus preparation: the following command will create documents from the corpus. Sed is used to remove the language prefix

sh bin/opennlp DoccatConverter leipzig -data ../eng_news_2010_300K-text/eng_news_2010_300K-sentences.txt -encoding UTF-8 -lang en | sed -E 's/^en[[:space:]]//g' > ../out-tokenized-documents.test

# Corpus preparation: this forces the detokenization of the documents

sh bin/opennlp SentenceDetectorConverter namefinder -data ../out-tokenized-documents.test -encoding UTF-8 -detokenizer trunk/opennlp-tools/lang/en/tokenizer/en-detokenizer.xml > ../out-documents.test

# Now the actually tests. Execute it for the previous release and for the current RC. Compare the output using diff:

time sh bin/opennlp SentenceDetector ../models/en-sent.bin < ../out-documents.test > ../out-sentences_1.5.2.test

time sh bin/opennlp TokenizerME ../models/en-token.bin < ../out-sentences_1.5.2.test > ../out-toks_1.5.2.test

time sh bin/opennlp TokenNameFinder ../models/en-ner-person.bin < ../out-toks_1.5.2.test > ../out-ner_1.5.2.test

time sh bin/opennlp POSTagger ../models/en-pos-maxent.bin < ../out-toks_1.5.2.test > ../out-pos_maxent_1.5.2.test

time sh bin/opennlp POSTagger ../models/en-pos-perceptron.bin < ../out-toks_1.5.2.test > ../out-pos_pers_1.5.2.test

time sh bin/opennlp ChunkerME ../models/en-chunker.bin < ../out-pos_pers_1.5.2.test > ../out-chk_1.5.2.test

time sh bin/opennlp Parser ../models/en-parser-chunking.bin < ../out-toks_1.5.2.test > ../out-parse_1.5.2.test