...
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 |
|
| William |
|
|
Tokenizer | en-token.bin |
|
| William |
|
|
Name Finder | en-ner-person.bin |
|
| William |
|
|
POS Tagger | en-pos-maxent.bin |
|
| William |
|
|
POS Tagger | en-pos-perceptron.bin |
|
| William |
|
|
Chunker | en-chunker.bin |
|
| William |
|
|
Parser | en-parser-chunking.bin |
|
| William |
|
|
Note: Test was done on Hardware
running Operational System
and Java Java Version
. The performance varies because light weight tasks have been performed in the background while testing.
...
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 |
| Precision: 0.7552941176470588 |
|
|
Name Finder | CONLL 2002 Dutch Person ned.testb |
| Precision: 0.8505025125628141 |
|
|
Name Finder | CONLL 2002 Dutch Organization ned.testa |
| Precision: 0.8561872909698997 |
|
|
Name Finder | CONLL 2002 Dutch Organization ned.testb |
| Precision: 0.7830374753451677 |
|
|
Name Finder | CONLL 2002 Dutch Location ned.testa |
| Precision: 0.8458333333333333 |
|
|
Name Finder | CONLL 2002 Dutch Location ned.testb |
| Precision: 0.8816326530612245 |
|
|
Name Finder | CONLL 2002 Dutch Misc ned.testa |
| Precision: 0.8354114713216958 |
|
|
Name Finder | CONLL 2002 Dutch Misc ned.testb |
| Precision: 0.8264984227129337 |
|
|
Name Finder | CONLL 2002 Combined ned.testa |
| Precision: 0.6509695290858726 |
| 1000 iterations |
Name Finder | CONLL 2002 Dutch Combined ned.testb |
| Precision: 0.6869929337869668 |
| 1000 iterations |
Name Finder | CONLL 2002 Spanish Person esp.testa |
| Precision: 0.9010695187165776 |
|
|
Name Finder | CONLL 2002 Spanish Person esp.testb |
| Precision: 0.9195205479452054 |
|
|
Name Finder | CONLL 2002 Spanish Organization esp.testa |
| Precision: 0.8288942695722357 |
|
|
Name Finder | CONLL 2002 Spanish Organization esp.testb |
| Precision: 0.8036277602523659 |
|
|
Name Finder | CONLL 2002 Spanish Location esp.testa |
| Precision: 0.7743016759776536 |
|
|
Name Finder | CONLL 2002 Spanish Location esp.testb |
| Precision: 0.8301886792452831 |
|
|
Name Finder | CONLL 2002 Spanish Misc esp.testa |
| Precision: 0.6492890995260664 |
|
|
Name Finder | CONLL 2002 Spanish Misc esp.testb |
| Precision: 0.686046511627907 |
|
|
Name Finder | CONLL 2002 Spanish Combined esp.testa |
| Precision: 0.7005423249233671 |
| 1000 iterations |
Name Finder | CONLL 2002 Spanish Combined esp.testb |
| Precision: 0.756635931824532 |
| 1000 iterations |
Name Finder | CONLL 2003 English Person eng.testa |
| Precision: 0.9523195876288659 |
|
|
Name Finder | CONLL 2003 English Person eng.testb |
| Precision: 0.9391727493917275 |
|
|
Name Finder | CONLL 2003 English Organization eng.testa |
| Precision: 0.8768046198267565 |
|
|
Name Finder | CONLL 2003 English Organization eng.testb |
| Precision: 0.8435980551053485 |
|
|
Name Finder | CONLL 2003 English Location eng.testa |
| Precision: 0.9361421988150099 |
|
|
Name Finder | CONLL 2003 English Location eng.testb |
| Precision: 0.9206349206349206 |
|
|
Name Finder | CONLL 2003 English Misc eng.testa |
| Precision: 0.9027982326951399 |
|
|
Name Finder | CONLL 2003 English Misc eng.testb |
| Precision: 0.8592436974789915 |
|
|
Name Finder | CONLL 2003 English Combined eng.testa |
| Precision: 0.861812521618817 |
| 1000 iterations |
Name Finder | CONLL 2003 English Combined eng.testb |
| Precision: 0.8041311831853597 |
| 1000 iterations |
Name Finder | CONLL 2003 German Person deu.testa |
| Precision: 0.9132653061224489 |
| |
Name Finder | CONLL 2003 German Person deu.testb |
| Precision: 0.8732106339468303 |
|
|
Name Finder | CONLL 2003 German Organization deu.testa |
| Precision: 0.8407224958949097 |
|
|
Name Finder | CONLL 2003 German Organization deu.testb |
| Precision: 0.8014705882352942 |
|
|
Name Finder | CONLL 2003 German Location deu.testa |
| Precision: 0.7816326530612245 |
|
|
Name Finder | CONLL 2003 German Location deu.testb |
| Precision: 0.8033826638477801 |
|
|
Name Finder | CONLL 2003 German Misc deu.testa |
| Precision: 0.7055555555555556 |
|
|
Name Finder | CONLL 2003 German Misc deu.testb |
| Precision: 0.6601307189542484 |
|
|
Name Finder | CONLL 2003 German Combined deu.testa |
| Precision: 0.7718859429714857 |
|
|
Name Finder | CONLL 2003 German Combined deu.testb |
| Precision: 0.7467566165023353 |
|
|
POS Tagger | CONLL 2006 Danish |
| Accuracy: 0.9511278195488722 |
|
|
POS Tagger | CONLL 2006 Dutch |
| Accuracy: 0.9324977618621307 |
|
|
POS Tagger | CONLL 2006 Portuguese |
| Accuracy: 0.9659110277825124 |
|
|
POS Tagger | CONLL 2006 Swedish |
| Accuracy: 0.9275106082036775 |
|
|
Chunker | CONLL 2000 | William | Precision: 0.9257575757575758 |
|
|
Chunker | Arvores Deitadas | William | Precision: 0.9403445830378374 |
|
|
...