/**
* Scores a tagging for a sentence. Note that a tag sequence not accepted by the markov process
* should receive a log score of Double.NEGATIVE_INFINITY.
*/
public double scoreTagging(TaggedSentence taggedSentence) {
double logScore = 0.0;
List<LabeledLocalTrigramContext> labeledLocalTrigramContexts =
extractLabeledLocalTrigramContexts(taggedSentence);
for (LabeledLocalTrigramContext labeledLocalTrigramContext : labeledLocalTrigramContexts) {
Counter<String> logScoreCounter =
localTrigramScorer.getLogScoreCounter(labeledLocalTrigramContext);
String currentTag = labeledLocalTrigramContext.getCurrentTag();
if (logScoreCounter.containsKey(currentTag)) {
logScore += logScoreCounter.getCount(currentTag);
} else {
logScore += Double.NEGATIVE_INFINITY;
}
}
return logScore;
}
public void train(List<LabeledLocalTrigramContext> labeledLocalTrigramContexts) {
// collect word-tag counts
for (LabeledLocalTrigramContext labeledLocalTrigramContext : labeledLocalTrigramContexts) {
String word = labeledLocalTrigramContext.getCurrentWord();
String tag = labeledLocalTrigramContext.getCurrentTag();
if (!wordsToTags.keySet().contains(word)) {
// word is currently unknown, so tally its tag in the unknown tag counter
unknownWordTags.incrementCount(tag, 1.0);
}
wordsToTags.incrementCount(word, tag, 1.0);
seenTagTrigrams.add(
makeTrigramString(
labeledLocalTrigramContext.getPreviousPreviousTag(),
labeledLocalTrigramContext.getPreviousTag(),
labeledLocalTrigramContext.getCurrentTag()));
}
wordsToTags = Counters.conditionalNormalize(wordsToTags);
unknownWordTags = Counters.normalize(unknownWordTags);
}