Please wait while GATE tools are initialised. /home/diana/gate/corpus_tool.properties New threshold is: 1.0

Annotation set in marked docs is: Key

Using annotation types from the properties file.

Features: []

App file is: /home/diana/sale/talks/gate-course-may10/track-3/module-9-advanced-ie/hands-on/corpus-benchmark/ANNIE-no-OM.gapp Processing directory: /home/diana/sale/talks/gate-course-may10/track-3/module-9-advanced-ie/hands-on/corpus-benchmark/test-corpus

ft-bank-of-uk-08-Aug-2001.xml


Word count: 435
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

1.0

1.0

 
Organization

1.0

0.6666666666666666

MISSING ANNOTATIONS in the automatic texts: Bank: [1325,1329] Bank: [471,475] Bank: [951,955]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Date

1.0

0.875

MISSING ANNOTATIONS in the automatic texts: end of the year: [1906,1921]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-equitable-09-aug-2001.xml


Word count: 269
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.25

0.5

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: City: [38,42]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: London: [46,52]
Organization

0.9166666666666667
Precision decrease on human-marked from 0.95 to 0.9166666666666667

0.45833333333333337
Recall decrease on human-marked from 0.7916666666666667 to 0.45833333333333337

MISSING ANNOTATIONS in the automatic texts: FSA: [691,694] Equitable: [524,533] FSA: [827,830] FSA: [500,503] Equitable: [228,237] FSA: [1358,1361]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Investment and Insurance: [707,731]
Date

1.0

1.0

 
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-bank-of-england-02-aug-2001.xml


Word count: 458
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.8

1.0

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: City: [1794,1798]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Organization

0.9
Precision decrease on human-marked from 0.90625 to 0.9

0.7941176470588235
Recall decrease on human-marked from 0.8529411764705882 to 0.7941176470588235

MISSING ANNOTATIONS in the automatic texts: Bank: [1817,1821] ECB: [2767,2770] Bank: [1511,1515]
SPURIOUS ANNOTATIONS in the automatic texts: Social: [2137,2143]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: National Institute of Economic: [2102,2132]
Date

0.875

0.5833333333333333

MISSING ANNOTATIONS in the automatic texts: Thursday: [1466,1474] second quarter: [1318,1332]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: 1964: [218,222]
Money

1.0

1.0

 
Percent

1.0

0.6666666666666666

MISSING ANNOTATIONS in the automatic texts: 0.25 percentage: [104,119]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:

ft-commerzbank-10-aug-2001.xml


Word count: 435
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

1.0

1.0

 
Organization

0.875

0.5384615384615385

MISSING ANNOTATIONS in the automatic texts: ABN Amro: [1488,1496] BSCH of Spain: [1515,1528] Soci�©t�© G�©n�©rale: [1438,1458] Assicurazioni Generali: [1118,1140] Comdirect: [1741,1750]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Fox: [2373,2376] Unicredito: [1013,1023]
Date

1.0

0.375

MISSING ANNOTATIONS in the automatic texts: end of the year: [548,563] first half: [2094,2104] third quarter: [1958,1971] second quarter: [172,186] second quarter: [277,291]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Money

0.8888888888888888

1.0

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: E27: [667,670]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Percent

1.0

1.0

 

ft-bmi-09-may-2001.xml


Word count: 378
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.9583333333333333

0.9583333333333333

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Washington: [532,542]
Organization

0.9545454545454546

0.8076923076923077

MISSING ANNOTATIONS in the automatic texts: Lufthansa: [444,453] Star: [901,905]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Lufthansa and SAS Scandinavian Airlines: [444,483]
Date

1.0

0.75

MISSING ANNOTATIONS in the automatic texts: first quarter: [1339,1352] first quarter: [1515,1528]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Money

0.8571428571428571

1.0

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: 20 US: [2143,2148]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Percent

1.0

1.0

 

ft-house-price-08-aug-2001.xml


Word count: 204
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.9444444444444444

0.9444444444444444

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: London: [441,447]
Organization

0.5

1.0

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: House: [0,5]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Date

0.9166666666666667

0.7857142857142857

MISSING ANNOTATIONS in the automatic texts: second quarter: [67,81]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: June: [761,765]
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-airlines-27-jul-2001.xml


Word count: 451
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.7777777777777778

0.7777777777777778

MISSING ANNOTATIONS in the automatic texts: Swanwick: [2376,2384] Swanwick: [2634,2642]
SPURIOUS ANNOTATIONS in the automatic texts: London: [388,394] London: [2029,2035]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Organization

0.8269230769230769

0.7678571428571429

MISSING ANNOTATIONS in the automatic texts: Britannia Airways: [1030,1047] London Underground: [388,406] Labour: [634,640]
SPURIOUS ANNOTATIONS in the automatic texts: Terminal Control Centre: [2045,2068]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Britannia Airways and Monarch Airlines: [1030,1068] Airline Group: [1270,1283] Airline Group: [942,955] Airline Group: [2416,2429] Airline Group: [1673,1686] Airline Group: [1755,1768] Area: [2036,2040]
Date

0.8333333333333333

0.8333333333333333

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: March: [1486,1491] March: [1743,1748] January: [2402,2409]
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-airtours-08-aug-2001.xml


Word count: 486
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.9583333333333333
Precision decrease on human-marked from 1.0 to 0.9583333333333333

0.9583333333333333
Recall decrease on human-marked from 1.0 to 0.9583333333333333

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Netherlands: [1662,1673]
Organization

1.0

1.0

 
Date

0.7857142857142857

0.6470588235294117

MISSING ANNOTATIONS in the automatic texts: winter: [2326,2332] third quarter: [123,136] first: [2788,2793]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: 2001: [2373,2377] 2001: [2480,2484] this year: [1211,1220] this year: [1575,1584] June 30: [248,255] 2001: [2277,2281]
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-equitable-07-auf-2001.xml


Word count: 346
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

0.0

1.0

MISSING ANNOTATIONS in the automatic texts:
SPURIOUS ANNOTATIONS in the automatic texts: City: [195,199]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Organization

0.5
Precision decrease on human-marked from 0.7142857142857143 to 0.5

0.2222222222222222
Recall decrease on human-marked from 0.5555555555555556 to 0.2222222222222222

MISSING ANNOTATIONS in the automatic texts: FSA: [681,684] Equitable: [1307,1316] Equitable: [428,437] FSA: [377,380] Equitable: [1552,1561] FSA: [2141,2144] Equitable: [1885,1894]
SPURIOUS ANNOTATIONS in the automatic texts: independent: [44,55] independent: [2163,2174]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Date

1.0

1.0

 
Money

1.0

1.0

 
Percent

1.0

1.0

 

ft-pirelli-10-aug-2001.xml


Word count: 301
Annotation Type Precision RecallAnnotations
Person

1.0

1.0

 
Location

1.0

1.0

 
Organization

0.7916666666666667
Precision increase on human-marked from 0.6129032258064516 to 0.7916666666666667

0.7307692307692307

MISSING ANNOTATIONS in the automatic texts: Benetton: [1427,1435] Benetton: [555,563] Bell: [637,641]
SPURIOUS ANNOTATIONS in the automatic texts: Italia: [210,216]
PARTIALLY CORRECT ANNOTATIONS in the automatic texts: Telecom: [449,456] Telecom: [202,209] Telecom: [54,61] Telecom: [870,877] Telecom: [319,326] Telecom: [1105,1112] Telecom: [1023,1030] Telecom: [372,379]
Date

1.0

0.7142857142857143

MISSING ANNOTATIONS in the automatic texts: this autumn: [1610,1621] a week ago: [118,128]
SPURIOUS ANNOTATIONS in the automatic texts:
PARTIALLY CORRECT ANNOTATIONS in the automatic texts:
Money

1.0

1.0

 
Percent

1.0

1.0

 
type = gate.corpora.DocumentImpl

Statistics

Annotation Type CorrectPartially Correct MissingSpurious PrecisionRecall F-Measure
Person 26 0 0 0 1.0 1.0 1.0
Location 54 4 2 5 0.8888888888888888 0.9333333333333333 0.9105691056910569
Organization 80 20 32 6 0.8490566037735849 0.6818181818181818 0.7563025210084033
Date 51 11 16 0 0.9112903225806451 0.7243589743589743 0.807142857142857
Money 69 0 0 2 0.971830985915493 1.0 0.9857142857142858
Percent 36 0 1 0 1.0 0.972972972972973 0.9863013698630138

Overall average precision: 0.9185072797572799
Overall average recall: 0.8892566855802151
Overall average fMeasure : 0.8851829370219236
Finished!