/* 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();
}