public void backpropDerivative(
Tree tree,
List<String> words,
IdentityHashMap<Tree, SimpleMatrix> nodeVectors,
TwoDimensionalMap<String, String, SimpleMatrix> binaryW_dfs,
Map<String, SimpleMatrix> unaryW_dfs,
TwoDimensionalMap<String, String, SimpleMatrix> binaryScoreDerivatives,
Map<String, SimpleMatrix> unaryScoreDerivatives,
Map<String, SimpleMatrix> wordVectorDerivatives,
SimpleMatrix deltaUp) {
if (tree.isLeaf()) {
return;
}
if (tree.isPreTerminal()) {
if (op.trainOptions.trainWordVectors) {
String word = tree.children()[0].label().value();
word = dvModel.getVocabWord(word);
// SimpleMatrix currentVector = nodeVectors.get(tree);
// SimpleMatrix currentVectorDerivative =
// nonlinearityVectorToDerivative(currentVector);
// SimpleMatrix derivative = deltaUp.elementMult(currentVectorDerivative);
SimpleMatrix derivative = deltaUp;
wordVectorDerivatives.put(word, wordVectorDerivatives.get(word).plus(derivative));
}
return;
}
SimpleMatrix currentVector = nodeVectors.get(tree);
SimpleMatrix currentVectorDerivative =
NeuralUtils.elementwiseApplyTanhDerivative(currentVector);
SimpleMatrix scoreW = dvModel.getScoreWForNode(tree);
currentVectorDerivative = currentVectorDerivative.elementMult(scoreW.transpose());
// the delta that is used at the current nodes
SimpleMatrix deltaCurrent = deltaUp.plus(currentVectorDerivative);
SimpleMatrix W = dvModel.getWForNode(tree);
SimpleMatrix WTdelta = W.transpose().mult(deltaCurrent);
if (tree.children().length == 2) {
// TODO: RS: Change to the nice "getWForNode" setup?
String leftLabel = dvModel.basicCategory(tree.children()[0].label().value());
String rightLabel = dvModel.basicCategory(tree.children()[1].label().value());
binaryScoreDerivatives.put(
leftLabel,
rightLabel,
binaryScoreDerivatives.get(leftLabel, rightLabel).plus(currentVector.transpose()));
SimpleMatrix leftVector = nodeVectors.get(tree.children()[0]);
SimpleMatrix rightVector = nodeVectors.get(tree.children()[1]);
SimpleMatrix childrenVector = NeuralUtils.concatenateWithBias(leftVector, rightVector);
if (op.trainOptions.useContextWords) {
childrenVector = concatenateContextWords(childrenVector, tree.getSpan(), words);
}
SimpleMatrix W_df = deltaCurrent.mult(childrenVector.transpose());
binaryW_dfs.put(leftLabel, rightLabel, binaryW_dfs.get(leftLabel, rightLabel).plus(W_df));
// and then recurse
SimpleMatrix leftDerivative = NeuralUtils.elementwiseApplyTanhDerivative(leftVector);
SimpleMatrix rightDerivative = NeuralUtils.elementwiseApplyTanhDerivative(rightVector);
SimpleMatrix leftWTDelta = WTdelta.extractMatrix(0, deltaCurrent.numRows(), 0, 1);
SimpleMatrix rightWTDelta =
WTdelta.extractMatrix(deltaCurrent.numRows(), deltaCurrent.numRows() * 2, 0, 1);
backpropDerivative(
tree.children()[0],
words,
nodeVectors,
binaryW_dfs,
unaryW_dfs,
binaryScoreDerivatives,
unaryScoreDerivatives,
wordVectorDerivatives,
leftDerivative.elementMult(leftWTDelta));
backpropDerivative(
tree.children()[1],
words,
nodeVectors,
binaryW_dfs,
unaryW_dfs,
binaryScoreDerivatives,
unaryScoreDerivatives,
wordVectorDerivatives,
rightDerivative.elementMult(rightWTDelta));
} else if (tree.children().length == 1) {
String childLabel = dvModel.basicCategory(tree.children()[0].label().value());
unaryScoreDerivatives.put(
childLabel, unaryScoreDerivatives.get(childLabel).plus(currentVector.transpose()));
SimpleMatrix childVector = nodeVectors.get(tree.children()[0]);
SimpleMatrix childVectorWithBias = NeuralUtils.concatenateWithBias(childVector);
if (op.trainOptions.useContextWords) {
childVectorWithBias = concatenateContextWords(childVectorWithBias, tree.getSpan(), words);
}
SimpleMatrix W_df = deltaCurrent.mult(childVectorWithBias.transpose());
// System.out.println("unary backprop derivative for " + childLabel);
// System.out.println("Old transform:");
// System.out.println(unaryW_dfs.get(childLabel));
// System.out.println(" Delta:");
// System.out.println(W_df.scale(scale));
unaryW_dfs.put(childLabel, unaryW_dfs.get(childLabel).plus(W_df));
// and then recurse
SimpleMatrix childDerivative = NeuralUtils.elementwiseApplyTanhDerivative(childVector);
// SimpleMatrix childDerivative = childVector;
SimpleMatrix childWTDelta = WTdelta.extractMatrix(0, deltaCurrent.numRows(), 0, 1);
backpropDerivative(
tree.children()[0],
words,
nodeVectors,
binaryW_dfs,
unaryW_dfs,
binaryScoreDerivatives,
unaryScoreDerivatives,
wordVectorDerivatives,
childDerivative.elementMult(childWTDelta));
}
}
private void forwardPropagateTree(
Tree tree,
List<String> words,
IdentityHashMap<Tree, SimpleMatrix> nodeVectors,
IdentityHashMap<Tree, Double> scores) {
if (tree.isLeaf()) {
return;
}
if (tree.isPreTerminal()) {
Tree wordNode = tree.children()[0];
String word = wordNode.label().value();
SimpleMatrix wordVector = dvModel.getWordVector(word);
wordVector = NeuralUtils.elementwiseApplyTanh(wordVector);
nodeVectors.put(tree, wordVector);
return;
}
for (Tree child : tree.children()) {
forwardPropagateTree(child, words, nodeVectors, scores);
}
// at this point, nodeVectors contains the vectors for all of
// the children of tree
SimpleMatrix childVec;
if (tree.children().length == 2) {
childVec =
NeuralUtils.concatenateWithBias(
nodeVectors.get(tree.children()[0]), nodeVectors.get(tree.children()[1]));
} else {
childVec = NeuralUtils.concatenateWithBias(nodeVectors.get(tree.children()[0]));
}
if (op.trainOptions.useContextWords) {
childVec = concatenateContextWords(childVec, tree.getSpan(), words);
}
SimpleMatrix W = dvModel.getWForNode(tree);
if (W == null) {
String error = "Could not find W for tree " + tree;
if (op.testOptions.verbose) {
System.err.println(error);
}
throw new NoSuchParseException(error);
}
SimpleMatrix currentVector = W.mult(childVec);
currentVector = NeuralUtils.elementwiseApplyTanh(currentVector);
nodeVectors.put(tree, currentVector);
SimpleMatrix scoreW = dvModel.getScoreWForNode(tree);
if (scoreW == null) {
String error = "Could not find scoreW for tree " + tree;
if (op.testOptions.verbose) {
System.err.println(error);
}
throw new NoSuchParseException(error);
}
double score = scoreW.dot(currentVector);
// score = NeuralUtils.sigmoid(score);
scores.put(tree, score);
// System.err.print(Double.toString(score)+" ");
}