/** This is (mostly) copied from CRF4.java */ public boolean[][] labelConnectionsIn( Alphabet outputAlphabet, InstanceList trainingSet, String start) { int numLabels = outputAlphabet.size(); boolean[][] connections = new boolean[numLabels][numLabels]; for (int i = 0; i < trainingSet.size(); i++) { Instance instance = trainingSet.getInstance(i); FeatureSequence output = (FeatureSequence) instance.getTarget(); for (int j = 1; j < output.size(); j++) { int sourceIndex = outputAlphabet.lookupIndex(output.get(j - 1)); int destIndex = outputAlphabet.lookupIndex(output.get(j)); assert (sourceIndex >= 0 && destIndex >= 0); connections[sourceIndex][destIndex] = true; } } // Handle start state if (start != null) { int startIndex = outputAlphabet.lookupIndex(start); for (int j = 0; j < outputAlphabet.size(); j++) { connections[startIndex][j] = true; } } return connections; }
public FeatureVector(FeatureSequence fs, boolean binary) { super(fs.toSortedFeatureIndexSequence(), false, false, true, binary); this.dictionary = (Alphabet) fs.getAlphabet(); }