@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);
}
}
public void train(List<SentencePair> trainingPairs) {
sourceTargetCounts = new CounterMap<String, String>();
sourceTargetDistortions = new CounterMap<Pair<Integer, Integer>, Pair<Integer, Integer>>();
for (SentencePair pair : trainingPairs) {
List<String> sourceSentence = pair.getSourceWords();
List<String> targetSentence = pair.getTargetWords();
targetSentence.add(WordAligner.NULL_WORD);
int m = sourceSentence.size();
int l = targetSentence.size();
for (int i = 0; i < m; i++) {
String sourceWord = sourceSentence.get(i);
for (int j = 0; j < l; j++) {
String targetWord = targetSentence.get(j);
sourceTargetCounts.setCount(sourceWord, targetWord, 1.0);
Pair<Integer, Integer> lmPair = new Pair<Integer, Integer>(l, m);
Pair<Integer, Integer> jiPair = new Pair<Integer, Integer>(j, i);
sourceTargetDistortions.setCount(jiPair, lmPair, 1.0);
}
}
}
// Use Model 1 to train params
double delta = Double.POSITIVE_INFINITY;
for (int i = 0; i < MAX_ITERS && delta > CONVERGENCE; i++) {
CounterMap<String, String> tempSourceTargetCounts = new CounterMap<String, String>();
Counter<String> targetCounts = new Counter<String>();
delta = 0.0;
for (SentencePair pair : trainingPairs) {
List<String> sourceSentence = pair.getSourceWords();
List<String> targetSentence = pair.getTargetWords();
Counter<String> sourceTotals = new Counter<String>();
for (String sourceWord : sourceSentence) {
for (String targetWord : targetSentence) {
sourceTotals.incrementCount(
sourceWord, sourceTargetCounts.getCount(sourceWord, targetWord));
}
}
for (String sourceWord : sourceSentence) {
for (String targetWord : targetSentence) {
double transProb = sourceTargetCounts.getCount(sourceWord, targetWord);
double sourceTotal = sourceTotals.getCount(sourceWord);
tempSourceTargetCounts.incrementCount(sourceWord, targetWord, transProb / sourceTotal);
targetCounts.incrementCount(targetWord, transProb / sourceTotal);
}
}
}
// update t(s|t) values
for (String sourceWord : tempSourceTargetCounts.keySet()) {
for (String targetWord : tempSourceTargetCounts.getCounter(sourceWord).keySet()) {
double oldProb = sourceTargetCounts.getCount(sourceWord, targetWord);
double newProb =
tempSourceTargetCounts.getCount(sourceWord, targetWord)
/ targetCounts.getCount(targetWord);
sourceTargetCounts.setCount(sourceWord, targetWord, newProb);
delta += Math.pow(oldProb - newProb, 2.0);
}
}
delta /= sourceTargetCounts.totalSize();
}
// Maximizing for ibm model 2
delta = Double.POSITIVE_INFINITY;
for (int iter = 0; iter < MAX_ITERS && delta > CONVERGENCE; iter++) {
CounterMap<String, String> tempSourceTargetCounts = new CounterMap<String, String>();
CounterMap<Pair<Integer, Integer>, Pair<Integer, Integer>> tempSourceTargetDistortions =
new CounterMap<Pair<Integer, Integer>, Pair<Integer, Integer>>();
Counter<String> targetCounts = new Counter<String>();
CounterMap<Pair<Integer, Integer>, Integer> targetDistorts =
new CounterMap<Pair<Integer, Integer>, Integer>();
delta = 0.0;
for (SentencePair pair : trainingPairs) {
List<String> sourceSentence = pair.getSourceWords();
List<String> targetSentence = pair.getTargetWords();
CounterMap<Pair<Integer, Integer>, Integer> distortSourceTotals =
new CounterMap<Pair<Integer, Integer>, Integer>();
Pair<Integer, Integer> lmPair =
new Pair<Integer, Integer>(targetSentence.size(), sourceSentence.size());
for (int i = 0; i < sourceSentence.size(); i++) {
String sourceWord = sourceSentence.get(i);
for (int j = 0; j < targetSentence.size(); j++) {
String targetWord = targetSentence.get(j);
Pair<Integer, Integer> jiPair = new Pair<Integer, Integer>(j, i);
double currTransProb = sourceTargetCounts.getCount(sourceWord, targetWord);
double currAlignProb = sourceTargetDistortions.getCount(jiPair, lmPair);
distortSourceTotals.incrementCount(lmPair, i, currTransProb * currAlignProb);
}
}
for (int i = 0; i < sourceSentence.size(); i++) {
String sourceWord = sourceSentence.get(i);
double distortTransSourceTotal = distortSourceTotals.getCount(lmPair, i);
for (int j = 0; j < targetSentence.size(); j++) {
String targetWord = targetSentence.get(j);
Pair<Integer, Integer> jiPair = new Pair<Integer, Integer>(j, i);
double transProb = sourceTargetCounts.getCount(sourceWord, targetWord);
double distortProb = sourceTargetDistortions.getCount(jiPair, lmPair);
double update =
(transProb * distortProb) / (distortTransSourceTotal); // q(j|ilm)t(f|e)/totals
tempSourceTargetCounts.incrementCount(sourceWord, targetWord, update);
tempSourceTargetDistortions.incrementCount(jiPair, lmPair, update);
targetCounts.incrementCount(targetWord, update);
targetDistorts.incrementCount(lmPair, i, update);
}
}
}
// update t(s|t) values
double delta_trans = 0.0;
for (String sourceWord : tempSourceTargetCounts.keySet()) {
for (String targetWord : tempSourceTargetCounts.getCounter(sourceWord).keySet()) {
double oldProb = sourceTargetCounts.getCount(sourceWord, targetWord);
double newProb =
tempSourceTargetCounts.getCount(sourceWord, targetWord)
/ targetCounts.getCount(targetWord);
sourceTargetCounts.setCount(sourceWord, targetWord, newProb);
delta += Math.pow(oldProb - newProb, 2.0);
}
}
// update q(j|ilm) values
double delta_dist = 0.0;
for (Pair<Integer, Integer> jiPair : tempSourceTargetDistortions.keySet()) {
for (Pair<Integer, Integer> lmPair :
tempSourceTargetDistortions.getCounter(jiPair).keySet()) {
double oldProb = sourceTargetDistortions.getCount(jiPair, lmPair);
double tempAlignProb = tempSourceTargetDistortions.getCount(jiPair, lmPair);
double tempTargetDist = targetDistorts.getCount(lmPair, jiPair.getSecond());
double newProb = tempAlignProb / tempTargetDist;
sourceTargetDistortions.setCount(jiPair, lmPair, newProb);
delta_dist += Math.pow(oldProb - newProb, 2.0);
}
}
delta =
(delta_trans / sourceTargetCounts.totalSize()
+ delta_dist / sourceTargetDistortions.totalSize())
/ 2.0;
}
}