文件列表:

personNER\personNER\mallet\bin\CVS\Entries (57, 2004-01-21)
personNER\personNER\mallet\bin\CVS\Repository (20, 2004-01-21)
personNER\personNER\mallet\bin\CVS\Root (31, 2004-01-21)
personNER\personNER\mallet\bin\personNER (319, 2004-01-21)
personNER\personNER\mallet\bin\prepend-license.sh (61, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\AccuracyCoverage$1.class (806, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\AccuracyCoverage$ClassificationComparator.class (1334, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\AccuracyCoverage.class (8136, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\ConfusionMatrix.class (5745, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\Graph$Legend.class (1848, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\Graph.class (4327, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\Graph2.class (2512, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\evaluate\GraphItem.class (562, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\examples\DocumentClassifier.class (3112, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\tests\TestClassifiers.class (4139, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\tests\TestMaxEntTrainer.class (2880, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\tests\TestNaiveBayes.class (7571, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\AccuracyEvaluator.class (1648, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\AdaBoost.class (1823, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\AdaBoostTrainer.class (4124, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\ApproximityPruning.class (6429, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\BaggingClassifier.class (1874, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\BaggingTrainer.class (2105, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\Boostable.class (133, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\Classification.class (2763, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\Classifier.class (6689, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\ClassifierEvaluating.class (364, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\ClassifierTrainer.class (8651, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\ConfidencePredictingClassifier.class (4329, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\ConfidencePredictingClassifierTrainer.class (5481, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\DecisionTree$Node.class (6798, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\DecisionTree.class (4881, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\DecisionTreeTrainer.class (4200, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\FeatureSelectingClassifierTrainer.class (1603, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\Kernel.class (2844, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\LinearKernel.class (870, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\MaxEnt.class (6733, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\MaxEnt2.class (14748, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\MaxEnt3.class (14596, 2004-01-21)
personNER\personNER\mallet\class\edu\umass\cs\mallet\base\classify\MaxEnt4.class (13904, 2004-01-21)
... ...

This directory contains a MALLET-based Person Name Extractor trained on ~1000 Enron email messages (calendar text entries, actually) labeled by William Cohen and others at CMU. We conducted a 4-fold cross validation on this data, and the average field-level F1 score is 0.8103. ********************************************* To run the program, type: mallet/bin/personNER outFile inFile1 inFile2 ... ********************************************* The program requires that java version 1.4.x be in your PATH. The argument "outFile" specifies a file in which to save the extraction results. This output is in the same "stand-off annotation" format used by William to label the data. The program will produce a large amount of diagnostic output on standard out, which can be ignored. (In fact, pipe it to /dev/null to increase speed.) Here's an example of output of running the Enron data: addToType baughman-d__calendar__1 237 11 predicted_name addToType baughman-d__calendar__11 584 11 predicted_name addToType baughman-d__calendar__11 849 13 predicted_name addToType baughman-d__calendar__12 161 5 predicted_name Each line corresponds to one person name. --- The first column can be ignored. --- The second column is the input file name. --- The third and fourth column are the start position of the person name and its length. --- The fifth column is the label. ********************************************* The arguments "inFile1 inFile2 ..." specify the input files. There are sample files under the directory "samples". And the program will use them as input if the user doesn't specify otherwise. ********************************************* If you have any questions, please contact Andrew McCallum or Wei Li, {mccallum,weili}@cs.umass.edu

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：