/// <summary>Train a segmenter from raw text.</summary>
/// <remarks>Train a segmenter from raw text. Gold segmentation markers are required.</remarks>
public virtual void Train()
{
bool hasSegmentationMarkers = true;
bool hasTags = true;
IDocumentReaderAndWriter <CoreLabel> docReader = new ArabicDocumentReaderAndWriter(hasSegmentationMarkers, hasTags, hasDomainLabels, domain, noRewrites, tf);
ObjectBank <IList <CoreLabel> > lines = classifier.MakeObjectBankFromFile(flags.trainFile, docReader);
classifier.Train(lines, docReader);
log.Info("Finished training.");
}
/// <exception cref="System.Exception"/>
public static void Main(string[] args)
{
StringUtils.LogInvocationString(log, args);
Properties props = StringUtils.ArgsToProperties(args);
CRFClassifier <CoreLabel> crf = new CRFClassifier <CoreLabel>(props);
string inputFile = crf.flags.trainFile;
if (inputFile == null)
{
log.Info("Please provide input file using -trainFile");
System.Environment.Exit(-1);
}
string outputFile = crf.flags.exportFeatures;
if (outputFile == null)
{
log.Info("Please provide output file using -exportFeatures");
System.Environment.Exit(-1);
}
Edu.Stanford.Nlp.IE.Crf.CRFFeatureExporter <CoreLabel> featureExporter = new Edu.Stanford.Nlp.IE.Crf.CRFFeatureExporter <CoreLabel>(crf);
ICollection <IList <CoreLabel> > docs = crf.MakeObjectBankFromFile(inputFile, crf.MakeReaderAndWriter());
crf.MakeAnswerArraysAndTagIndex(docs);
featureExporter.PrintFeatures(outputFile, docs);
}