ngramfeatureGen

de.uniwue.ls6.rulelearning/InstanceLoading/src/de/uniwue/ls6/rulelearning/instanceloading/featuregenerator/NGramGenerator.java

+package de.uniwue.ls6.rulelearning.instanceloading.featuregenerator;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.uima.cas.text.AnnotationFS;
+
+public class NGramGenerator extends AFeatureGenerator {
+
+
+	public NGramGenerator() {
+		super("NGram");
+	}
+
+	@Override
+	public String[] generateFeatures(AnnotationFS token) {
+		String text = token.getCoveredText();
+		int len = text.length();
+		List<String> ngrams = new ArrayList<String>();
+		for (int beg = 0; beg < len; beg++) {
+			for (int end = beg + 1; end <= len; end++) {
+				String ngram = text.substring(beg, end);
+				if (beg > 0)
+					ngram = "*" + ngram;
+				if (end < len )
+					ngram += "*";
+				
+				ngrams.add(super.featureIdentifier + "=" +ngram);
+			}
+		}
+		return ngrams.toArray(new String[0]);
+	}
+
+}

de.uniwue.ls6.rulelearning/InstanceLoading/src/de/uniwue/ls6/rulelearning/instanceloading/featuregenerator/NNFeatureGenerator.java

@@ -16,7 +16,7 @@ public class NNFeatureGenerator extends AFeatureGenerator{
 	public String[] generateFeatures(AnnotationFS token) {
 		
 		String featureValueAsString = token.getFeatureValueAsString(token.getType().getFeatureByBaseName(posTagFeature));
-		return new String[]{featureValueAsString.startsWith("VVFIN")?super.featureIdentifier+"=NN":super.featureIdentifier+"=O"};
+		return new String[]{featureValueAsString.startsWith("N")?super.featureIdentifier+"=NN":super.featureIdentifier+"=O"};
 	}
 
 }

de.uniwue.ls6.rulelearning/RuleLearning/src/test/FirstTest2.java

@@ -14,6 +14,7 @@ import de.uniwue.ls6.datastructure.Instance;
 import de.uniwue.ls6.datastructure.LabelAlphabet;
 import de.uniwue.ls6.rulelearning.algorithm.impl.BinaryRepresentationRuleLearningAlgorithm;
 import de.uniwue.ls6.rulelearning.instanceloading.featuregenerator.IsUppercaseFeatureGenerator;
+import de.uniwue.ls6.rulelearning.instanceloading.featuregenerator.NGramGenerator;
 import de.uniwue.ls6.rulelearning.instanceloading.featuregenerator.NNFeatureGenerator;
 import de.uniwue.ls6.rulelearning.instanceloading.featuregenerator.PrefixNGenerator;
 import de.uniwue.ls6.rulelearning.instanceloading.featuregenerator.SuffixNGenerator;
@@ -43,7 +44,7 @@ public class FirstTest2 {
 					"de.uniwue.kalimachos.coref.type.POS", tsd, new NNFeatureGenerator("POSTag"),
 					new WordFeaturegenerator(), new SuffixNGenerator(4), new SuffixNGenerator(3),
 					new SuffixNGenerator(2), new SuffixNGenerator(1), new PrefixNGenerator(1), new PrefixNGenerator(2),
-					new IsUppercaseFeatureGenerator(), new PrefixNGenerator(3)));
+					new IsUppercaseFeatureGenerator(), new PrefixNGenerator(3), new NGramGenerator()));
 			System.out.println("instances: " + instances.size());
 			//if(instances.size()>20000)break;
 		}