/** Outputs the scores from the tree. Counts the tree nodes the same as setIndexLabels. */
static int outputTreeScores(PrintStream out, Tree tree, int index) {
if (tree.isLeaf()) {
return index;
}
out.print(" " + index + ":");
SimpleMatrix vector = RNNCoreAnnotations.getPredictions(tree);
for (int i = 0; i < vector.getNumElements(); ++i) {
out.print(" " + NF.format(vector.get(i)));
}
out.println();
index++;
for (Tree child : tree.children()) {
index = outputTreeScores(out, child, index);
}
return index;
}
private SentimentModel(
TwoDimensionalMap<String, String, SimpleMatrix> binaryTransform,
TwoDimensionalMap<String, String, SimpleTensor> binaryTensors,
TwoDimensionalMap<String, String, SimpleMatrix> binaryClassification,
Map<String, SimpleMatrix> unaryClassification,
Map<String, SimpleMatrix> wordVectors,
RNNOptions op) {
this.op = op;
this.binaryTransform = binaryTransform;
this.binaryTensors = binaryTensors;
this.binaryClassification = binaryClassification;
this.unaryClassification = unaryClassification;
this.wordVectors = wordVectors;
this.numClasses = op.numClasses;
if (op.numHid <= 0) {
int nh = 0;
for (SimpleMatrix wv : wordVectors.values()) {
nh = wv.getNumElements();
}
this.numHid = nh;
} else {
this.numHid = op.numHid;
}
this.numBinaryMatrices = binaryTransform.size();
binaryTransformSize = numHid * (2 * numHid + 1);
if (op.useTensors) {
binaryTensorSize = numHid * numHid * numHid * 4;
} else {
binaryTensorSize = 0;
}
binaryClassificationSize = (op.combineClassification) ? 0 : numClasses * (numHid + 1);
numUnaryMatrices = unaryClassification.size();
unaryClassificationSize = numClasses * (numHid + 1);
rand = new Random(op.randomSeed);
identity = SimpleMatrix.identity(numHid);
}
/** The traditional way of initializing an empty model suitable for training. */
public SentimentModel(RNNOptions op, List<Tree> trainingTrees) {
this.op = op;
rand = new Random(op.randomSeed);
if (op.randomWordVectors) {
initRandomWordVectors(trainingTrees);
} else {
readWordVectors();
}
if (op.numHid > 0) {
this.numHid = op.numHid;
} else {
int size = 0;
for (SimpleMatrix vector : wordVectors.values()) {
size = vector.getNumElements();
break;
}
this.numHid = size;
}
TwoDimensionalSet<String, String> binaryProductions = TwoDimensionalSet.hashSet();
if (op.simplifiedModel) {
binaryProductions.add("", "");
} else {
// TODO
// figure out what binary productions we have in these trees
// Note: the current sentiment training data does not actually
// have any constituent labels
throw new UnsupportedOperationException("Not yet implemented");
}
Set<String> unaryProductions = Generics.newHashSet();
if (op.simplifiedModel) {
unaryProductions.add("");
} else {
// TODO
// figure out what unary productions we have in these trees (preterminals only, after the
// collapsing)
throw new UnsupportedOperationException("Not yet implemented");
}
this.numClasses = op.numClasses;
identity = SimpleMatrix.identity(numHid);
binaryTransform = TwoDimensionalMap.treeMap();
binaryTensors = TwoDimensionalMap.treeMap();
binaryClassification = TwoDimensionalMap.treeMap();
// When making a flat model (no symantic untying) the
// basicCategory function will return the same basic category for
// all labels, so all entries will map to the same matrix
for (Pair<String, String> binary : binaryProductions) {
String left = basicCategory(binary.first);
String right = basicCategory(binary.second);
if (binaryTransform.contains(left, right)) {
continue;
}
binaryTransform.put(left, right, randomTransformMatrix());
if (op.useTensors) {
binaryTensors.put(left, right, randomBinaryTensor());
}
if (!op.combineClassification) {
binaryClassification.put(left, right, randomClassificationMatrix());
}
}
numBinaryMatrices = binaryTransform.size();
binaryTransformSize = numHid * (2 * numHid + 1);
if (op.useTensors) {
binaryTensorSize = numHid * numHid * numHid * 4;
} else {
binaryTensorSize = 0;
}
binaryClassificationSize = (op.combineClassification) ? 0 : numClasses * (numHid + 1);
unaryClassification = Generics.newTreeMap();
// When making a flat model (no symantic untying) the
// basicCategory function will return the same basic category for
// all labels, so all entries will map to the same matrix
for (String unary : unaryProductions) {
unary = basicCategory(unary);
if (unaryClassification.containsKey(unary)) {
continue;
}
unaryClassification.put(unary, randomClassificationMatrix());
}
numUnaryMatrices = unaryClassification.size();
unaryClassificationSize = numClasses * (numHid + 1);
// System.err.println("Binary transform matrices:");
// System.err.println(binaryTransform);
// System.err.println("Binary classification matrices:");
// System.err.println(binaryClassification);
// System.err.println("Unary classification matrices:");
// System.err.println(unaryClassification);
}