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 void tallyTagging(String word, String tag) {
if (!isKnown(word)) {
totalWordTypes += 1.0;
typeTagCounter.incrementCount(tag, 1.0);
}
totalTokens += 1.0;
tagCounter.incrementCount(tag, 1.0);
wordCounter.incrementCount(word, 1.0);
wordToTagCounters.incrementCount(word, tag, 1.0);
}
/* Returns a smoothed estimate of P(word|tag) */
public double scoreTagging(String word, String tag) {
double p_tag = tagCounter.getCount(tag) / totalTokens;
double c_word = wordCounter.getCount(word);
double c_tag_and_word = wordToTagCounters.getCount(word, tag);
if (c_word < 10) { // rare or unknown
c_word += 1.0;
c_tag_and_word += typeTagCounter.getCount(tag) / totalWordTypes;
}
double p_word = (1.0 + c_word) / (totalTokens + totalWordTypes);
double p_tag_given_word = c_tag_and_word / c_word;
return p_tag_given_word / p_tag * p_word;
}
/* A builds PCFG using the observed counts of binary and unary
* productions in the training trees to estimate the probabilities
* for those rules.
*/
public Grammar(List<Tree<String>> trainTrees) {
Counter<UnaryRule> unaryRuleCounter = new Counter<UnaryRule>();
Counter<BinaryRule> binaryRuleCounter = new Counter<BinaryRule>();
Counter<String> symbolCounter = new Counter<String>();
for (Tree<String> trainTree : trainTrees) {
tallyTree(trainTree, symbolCounter, unaryRuleCounter, binaryRuleCounter);
}
for (UnaryRule unaryRule : unaryRuleCounter.keySet()) {
double unaryProbability =
unaryRuleCounter.getCount(unaryRule) / symbolCounter.getCount(unaryRule.getParent());
unaryRule.setScore(unaryProbability);
addUnary(unaryRule);
}
for (BinaryRule binaryRule : binaryRuleCounter.keySet()) {
double binaryProbability =
binaryRuleCounter.getCount(binaryRule) / symbolCounter.getCount(binaryRule.getParent());
binaryRule.setScore(binaryProbability);
addBinary(binaryRule);
}
}
public boolean isKnown(String word) {
return wordCounter.keySet().contains(word);
}
public Set<String> getAllTags() {
return tagCounter.keySet();
}