public List<ClusteredMention> runCoreference(Document doc) {
// --Overhead
startTrack("Testing " + doc.id);
// (variables)
List<ClusteredMention> rtn = new ArrayList<ClusteredMention>(doc.getMentions().size());
List<Mention> mentions = doc.getMentions();
int singletons = 0;
// --Run Classifier
for (int i = 0; i < mentions.size(); i++) {
// (variables)
Mention onPrix = mentions.get(i);
int coreferentWith = -1;
// (get mention it is coreferent with)
for (int j = i - 1; j >= 0; j--) {
ClusteredMention cand = rtn.get(j);
boolean coreferent =
classifier.classOf(
new RVFDatum<Boolean, Feature>(extractor.extractFeatures(Pair.make(onPrix, cand))));
if (coreferent) {
coreferentWith = j;
break;
}
}
if (coreferentWith < 0) {
singletons += 1;
rtn.add(onPrix.markSingleton());
} else {
// log("Mention " + onPrix + " coreferent with " + mentions.get(coreferentWith));
rtn.add(onPrix.markCoreferent(rtn.get(coreferentWith)));
}
}
// log("" + singletons + " singletons");
// --Return
endTrack("Testing " + doc.id);
return rtn;
}
public void train(Collection<Pair<Document, List<Entity>>> trainingData) {
startTrack("Training");
// --Variables
RVFDataset<Boolean, Feature> dataset = new RVFDataset<Boolean, Feature>();
LinearClassifierFactory<Boolean, Feature> fact =
new LinearClassifierFactory<Boolean, Feature>();
// --Feature Extraction
startTrack("Feature Extraction");
for (Pair<Document, List<Entity>> datum : trainingData) {
// (document variables)
Document doc = datum.getFirst();
List<Entity> goldClusters = datum.getSecond();
List<Mention> mentions = doc.getMentions();
Map<Mention, Entity> goldEntities = Entity.mentionToEntityMap(goldClusters);
startTrack("Document " + doc.id);
// (for each mention...)
for (int i = 0; i < mentions.size(); i++) {
// (get the mention and its cluster)
Mention onPrix = mentions.get(i);
Entity source = goldEntities.get(onPrix);
if (source == null) {
throw new IllegalArgumentException("Mention has no gold entity: " + onPrix);
}
// (for each previous mention...)
int oldSize = dataset.size();
for (int j = i - 1; j >= 0; j--) {
// (get previous mention and its cluster)
Mention cand = mentions.get(j);
Entity target = goldEntities.get(cand);
if (target == null) {
throw new IllegalArgumentException("Mention has no gold entity: " + cand);
}
// (extract features)
Counter<Feature> feats =
extractor.extractFeatures(Pair.make(onPrix, cand.markCoreferent(target)));
// (add datum)
dataset.add(new RVFDatum<Boolean, Feature>(feats, target == source));
// (stop if
if (target == source) {
break;
}
}
// logf("Mention %s (%d datums)", onPrix.toString(), dataset.size() - oldSize);
}
endTrack("Document " + doc.id);
}
endTrack("Feature Extraction");
// --Train Classifier
startTrack("Minimizer");
this.classifier = fact.trainClassifier(dataset);
endTrack("Minimizer");
// --Dump Weights
startTrack("Features");
// (get labels to print)
Set<Boolean> labels = new HashSet<Boolean>();
labels.add(true);
// (print features)
for (Triple<Feature, Boolean, Double> featureInfo :
this.classifier.getTopFeatures(labels, 0.0, true, 100, true)) {
Feature feature = featureInfo.first();
Boolean label = featureInfo.second();
Double magnitude = featureInfo.third();
// log(FORCE,new DecimalFormat("0.000").format(magnitude) + " [" + label + "] " + feature);
}
end_Track("Features");
endTrack("Training");
}