private void tallyTree(
Tree<String> tree,
Counter<String> symbolCounter,
Counter<UnaryRule> unaryRuleCounter,
Counter<BinaryRule> binaryRuleCounter) {
if (tree.isLeaf()) return;
if (tree.isPreTerminal()) return;
if (tree.getChildren().size() == 1) {
UnaryRule unaryRule = makeUnaryRule(tree);
symbolCounter.incrementCount(tree.getLabel(), 1.0);
unaryRuleCounter.incrementCount(unaryRule, 1.0);
}
if (tree.getChildren().size() == 2) {
BinaryRule binaryRule = makeBinaryRule(tree);
symbolCounter.incrementCount(tree.getLabel(), 1.0);
binaryRuleCounter.incrementCount(binaryRule, 1.0);
}
if (tree.getChildren().size() < 1 || tree.getChildren().size() > 2) {
throw new RuntimeException(
"Attempted to construct a Grammar with an illegal tree: " + tree);
}
for (Tree<String> child : tree.getChildren()) {
tallyTree(child, symbolCounter, unaryRuleCounter, binaryRuleCounter);
}
}
private static Tree<String> binarizeTree(Tree<String> tree) {
String label = tree.getLabel();
if (tree.isLeaf()) {
return new Tree<String>(label);
}
/*
// [Average] P: 48.53 R: 47.67 F1: 48.10 EX: 4.85
if (tree.getChildren().size() == 1) {
return new Tree<String>(label, Collections.singletonList(binarizeTree(tree.getChildren().get(0))));
}
*/
// [Average] P: 48.53 R: 47.67 F1: 48.10 EX: 4.85
if (tree.getChildren().size() <= 2) {
List<Tree<String>> children = new ArrayList<Tree<String>>(2);
for (Tree<String> child : tree.getChildren()) {
children.add(binarizeTree(child));
}
return new Tree<String>(label, children);
}
// otherwise, it's a binary-or-more local tree,
// so decompose it into a sequence of binary and unary trees.
String intermediateLabel = "@" + label + "->";
Tree<String> intermediateTree = binarizeTreeHelper(tree, 0, intermediateLabel);
return new Tree<String>(label, intermediateTree.getChildren());
}
private static <L> void appendYield(Tree<L> tree, List<L> yield) {
if (tree.isLeaf()) {
yield.add(tree.getLabel());
return;
}
for (Tree<L> child : tree.getChildren()) {
appendYield(child, yield);
}
}
private static <L> int toConstituentCollectionHelper(
Tree<L> tree, int start, List<Constituent<L>> constituents) {
if (tree.isLeaf() || tree.isPreTerminal()) return 1;
int span = 0;
for (Tree<L> child : tree.getChildren()) {
span += toConstituentCollectionHelper(child, start + span, constituents);
}
constituents.add(new Constituent<L>(tree.getLabel(), start, start + span));
return span;
}
private int tallySpans(Tree<String> tree, int start) {
if (tree.isLeaf() || tree.isPreTerminal()) return 1;
int end = start;
for (Tree<String> child : tree.getChildren()) {
int childSpan = tallySpans(child, end);
end += childSpan;
}
String category = tree.getLabel();
if (!category.equals("ROOT")) spanToCategories.incrementCount(end - start, category, 1.0);
return end - start;
}