public virtual void RunCoref(Document document)
{
IList <Mention> sortedMentions = CorefUtils.GetSortedMentions(document);
IDictionary <int, IList <Mention> > mentionsByHeadIndex = new Dictionary <int, IList <Mention> >();
foreach (Mention m in sortedMentions)
{
IList <Mention> withIndex = mentionsByHeadIndex.ComputeIfAbsent(m.headIndex, null);
withIndex.Add(m);
}
SimpleMatrix documentEmbedding = embeddingExtractor.GetDocumentEmbedding(document);
IDictionary <int, SimpleMatrix> antecedentEmbeddings = new Dictionary <int, SimpleMatrix>();
IDictionary <int, SimpleMatrix> anaphorEmbeddings = new Dictionary <int, SimpleMatrix>();
ICounter <int> anaphoricityScores = new ClassicCounter <int>();
foreach (Mention m_1 in sortedMentions)
{
SimpleMatrix mentionEmbedding = embeddingExtractor.GetMentionEmbeddings(m_1, documentEmbedding);
antecedentEmbeddings[m_1.mentionID] = model.GetAntecedentEmbedding(mentionEmbedding);
anaphorEmbeddings[m_1.mentionID] = model.GetAnaphorEmbedding(mentionEmbedding);
anaphoricityScores.IncrementCount(m_1.mentionID, model.GetAnaphoricityScore(mentionEmbedding, featureExtractor.GetAnaphoricityFeatures(m_1, document, mentionsByHeadIndex)));
}
IDictionary <int, IList <int> > mentionToCandidateAntecedents = CorefUtils.HeuristicFilter(sortedMentions, maxMentionDistance, maxMentionDistanceWithStringMatch);
foreach (KeyValuePair <int, IList <int> > e in mentionToCandidateAntecedents)
{
double bestScore = anaphoricityScores.GetCount(e.Key) - 50 * (greedyness - 0.5);
int m_2 = e.Key;
int antecedent = null;
foreach (int ca in e.Value)
{
double score = model.GetPairwiseScore(antecedentEmbeddings[ca], anaphorEmbeddings[m_2], featureExtractor.GetPairFeatures(new Pair <int, int>(ca, m_2), document, mentionsByHeadIndex));
if (score > bestScore)
{
bestScore = score;
antecedent = ca;
}
}
if (antecedent != null)
{
CorefUtils.MergeCoreferenceClusters(new Pair <int, int>(antecedent, m_2), document);
}
}
}
