public static IDictionary <Pair <int, int>, bool> GetUnlabeledMentionPairs(Document document)
{
return(CorefUtils.GetMentionPairs(document).Stream().Collect(Collectors.ToMap(null, null)));
}
public virtual void Process(int id, Document document)
{
// Mention types
mentionTypes[id] = document.predictedMentionsByID.Stream().Collect(Collectors.ToMap(null, null));
// Gold clusters
IList <IList <int> > clusters = new List <IList <int> >();
foreach (CorefCluster c in document.goldCorefClusters.Values)
{
IList <int> cluster = new List <int>();
foreach (Mention m in c.GetCorefMentions())
{
cluster.Add(m.mentionID);
}
clusters.Add(cluster);
}
goldClusters[id] = clusters;
// Word counting
if (countWords && mentionPairs.Contains(id))
{
ICollection <Pair <int, int> > pairs = mentionPairs[id].Keys;
ICollection <int> mentions = new HashSet <int>();
foreach (Pair <int, int> pair in pairs)
{
mentions.Add(pair.first);
mentions.Add(pair.second);
Mention m1 = document.predictedMentionsByID[pair.first];
Mention m2 = document.predictedMentionsByID[pair.second];
wordCounts.IncrementCount("h_" + m1.headWord.Word().ToLower() + "_" + m2.headWord.Word().ToLower());
}
IDictionary <int, IList <CoreLabel> > sentences = new Dictionary <int, IList <CoreLabel> >();
foreach (int mention in mentions)
{
Mention m = document.predictedMentionsByID[mention];
if (!sentences.Contains(m.sentNum))
{
sentences[m.sentNum] = m.sentenceWords;
}
}
foreach (IList <CoreLabel> sentence in sentences.Values)
{
for (int i = 0; i < sentence.Count; i++)
{
CoreLabel cl = sentence[i];
if (cl == null)
{
continue;
}
string w = cl.Word().ToLower();
wordCounts.IncrementCount(w);
if (i > 0)
{
CoreLabel clp = sentence[i - 1];
if (clp == null)
{
continue;
}
string wp = clp.Word().ToLower();
wordCounts.IncrementCount(wp + "_" + w);
}
}
}
}
}
public virtual void Update(IList <IList <int> > gold, IList <Clusterer.Cluster> clusters, IDictionary <int, IList <int> > mentionToGold, IDictionary <int, Clusterer.Cluster> mentionToSystem)
{
IList <IList <int> > clustersAsList = clusters.Stream().Map(null).Collect(Collectors.ToList());
IDictionary <int, IList <int> > mentionToSystemLists = mentionToSystem.Stream().Collect(Collectors.ToMap(null, null));
Pair <double, double> prec = GetScore(clustersAsList, mentionToGold);
Pair <double, double> rec = GetScore(gold, mentionToSystemLists);
pNum += prec.first;
pDen += prec.second;
rNum += rec.first;
rDen += rec.second;
}
public virtual void RunCoref(Document document)
{
IDictionary <Pair <int, int>, bool> mentionPairs = CorefUtils.GetUnlabeledMentionPairs(document);
if (mentionPairs.Count == 0)
{
return;
}
Compressor <string> compressor = new Compressor <string>();
DocumentExamples examples = extractor.Extract(0, document, mentionPairs, compressor);
ICounter <Pair <int, int> > classificationScores = new ClassicCounter <Pair <int, int> >();
ICounter <Pair <int, int> > rankingScores = new ClassicCounter <Pair <int, int> >();
ICounter <int> anaphoricityScores = new ClassicCounter <int>();
foreach (Example example in examples.examples)
{
CorefUtils.CheckForInterrupt();
Pair <int, int> mentionPair = new Pair <int, int>(example.mentionId1, example.mentionId2);
classificationScores.IncrementCount(mentionPair, classificationModel.Predict(example, examples.mentionFeatures, compressor));
rankingScores.IncrementCount(mentionPair, rankingModel.Predict(example, examples.mentionFeatures, compressor));
if (!anaphoricityScores.ContainsKey(example.mentionId2))
{
anaphoricityScores.IncrementCount(example.mentionId2, anaphoricityModel.Predict(new Example(example, false), examples.mentionFeatures, compressor));
}
}
ClustererDataLoader.ClustererDoc doc = new ClustererDataLoader.ClustererDoc(0, classificationScores, rankingScores, anaphoricityScores, mentionPairs, null, document.predictedMentionsByID.Stream().Collect(Collectors.ToMap(null, null)));
foreach (Pair <int, int> mentionPair_1 in clusterer.GetClusterMerges(doc))
{
CorefUtils.MergeCoreferenceClusters(mentionPair_1, document);
}
}
