@SuppressWarnings({"unchecked"})
@Override
protected void fillFeatures(
Pair<Mention, ClusteredMention> input,
Counter<Feature> inFeatures,
Boolean output,
Counter<Feature> outFeatures) {
// --Input Features
for (Object o : ACTIVE_FEATURES) {
if (o instanceof Class) {
// (case: singleton feature)
Option<Double> count = new Option<Double>(1.0);
Feature feat = feature((Class) o, input, count);
if (count.get() > 0.0) {
inFeatures.incrementCount(feat, count.get());
}
} else if (o instanceof Pair) {
// (case: pair of features)
Pair<Class, Class> pair = (Pair<Class, Class>) o;
Option<Double> countA = new Option<Double>(1.0);
Option<Double> countB = new Option<Double>(1.0);
Feature featA = feature(pair.getFirst(), input, countA);
Feature featB = feature(pair.getSecond(), input, countB);
if (countA.get() * countB.get() > 0.0) {
inFeatures.incrementCount(
new Feature.PairFeature(featA, featB), countA.get() * countB.get());
}
}
}
// --Output Features
if (output != null) {
outFeatures.incrementCount(new Feature.CoreferentIndicator(output), 1.0);
}
}
private <E> Feature feature(
Class<E> clazz, Pair<Mention, ClusteredMention> input, Option<Double> count) {
// --Variables
Mention onPrix =
input.getFirst(); // the first mention (referred to as m_i in the handout)
Mention candidate =
input.getSecond().mention; // the second mention (referred to as m_j in the handout)
Entity candidateCluster =
input.getSecond().entity; // the cluster containing the second mention
// --Features:w
if (clazz.equals(Feature.ExactMatch.class)) {
// (exact string match)
return new Feature.ExactMatch(onPrix.gloss().equals(candidate.gloss()));
} else if (clazz.equals(Feature.SentenceDist.class)) {
return new Feature.SentenceDist(
Math.abs(
onPrix.doc.indexOfMention(onPrix) - candidate.doc.indexOfMention(candidate)));
} else if (clazz.equals(Feature.MentionDist.class)) {
return new Feature.MentionDist(
Math.abs(
onPrix.doc.indexOfSentence(onPrix.sentence)
- candidate.doc.indexOfSentence(candidate.sentence)));
} else if (clazz.equals(Feature.EitherHeadWordPronoun.class)) {
return new Feature.EitherHeadWordPronoun(
Pronoun.isSomePronoun(onPrix.gloss()) || Pronoun.isSomePronoun(candidate.gloss()));
} else if (clazz.equals(Feature.CandidateNERTag.class)) {
return new Feature.CandidateNERTag(candidate.headToken().nerTag());
} else if (clazz.equals(Feature.CandidateSpeaker.class)) {
return new Feature.CandidateSpeaker(candidate.headToken().speaker());
} else if (clazz.equals(Feature.FixedSpeaker.class)) {
return new Feature.FixedSpeaker(onPrix.headToken().speaker());
} else if (clazz.equals(Feature.HeadWordMatch.class)) {
return new Feature.HeadWordMatch(onPrix.equals(candidate.headWord()));
} else if (clazz.equals(Feature.HeadWordLemmaMatch.class)) {
return new Feature.HeadWordLemmaMatch(
onPrix.headToken().lemma().equals(candidate.headToken().lemma()));
} else if (clazz.equals(Feature.FixedNERTag.class)) {
return new Feature.FixedNERTag(onPrix.headToken().nerTag());
} else if (clazz.equals(Feature.SpeakerMatch.class)) {
return new Feature.SpeakerMatch(
candidate.headToken().speaker().equals(onPrix.headToken().speaker()));
} else if (clazz.equals(Feature.NERTagMatch.class)) {
return new Feature.NERTagMatch(
candidate.headToken().nerTag().equals(onPrix.headToken().nerTag()));
} else if (clazz.equals(Feature.CandidatePOSTag.class)) {
return new Feature.CandidatePOSTag(candidate.headToken().posTag());
} else if (clazz.equals(Feature.FixedPOSTag.class)) {
return new Feature.FixedPOSTag(onPrix.headToken().posTag());
} else if (clazz.equals(Feature.GenderMatch.class)) {
Pair<Boolean, Boolean> match = Util.haveGenderAndAreSameGender(onPrix, candidate);
boolean finalMatch = (!match.getFirst() || match.getSecond());
return new Feature.GenderMatch(finalMatch);
} else if (clazz.equals(Feature.NumberMatch.class)) {
Pair<Boolean, Boolean> match = Util.haveNumberAndAreSameNumber(onPrix, candidate);
boolean finalMatch = (!match.getFirst() || match.getSecond());
return new Feature.NumberMatch(finalMatch);
}
// } else if(clazz.equals(Feature.NewFeature.class) {
/*
* TODO: Add features to return for specific classes. Implement calculating values of features here.
*/
else {
throw new IllegalArgumentException("Unregistered feature: " + clazz);
}
}
