/// <exception cref="System.Exception"/>
public static void TrainClassification(PairwiseModel model, bool anaphoricityModel)
{
int numTrainingExamples = model.GetNumTrainingExamples();
Redwood.Log("scoref-train", "Reading compression...");
Compressor <string> compressor = IOUtils.ReadObjectFromFile(StatisticalCorefTrainer.compressorFile);
Redwood.Log("scoref-train", "Reading train data...");
IList <DocumentExamples> trainDocuments = IOUtils.ReadObjectFromFile(StatisticalCorefTrainer.extractedFeaturesFile);
Redwood.Log("scoref-train", "Building train set...");
IList <Pair <Example, IDictionary <int, CompressedFeatureVector> > > allExamples = anaphoricityModel ? GetAnaphoricityExamples(trainDocuments) : GetExamples(trainDocuments);
Redwood.Log("scoref-train", "Training...");
Random random = new Random(0);
int i = 0;
bool stopTraining = false;
while (!stopTraining)
{
Java.Util.Collections.Shuffle(allExamples, random);
foreach (Pair <Example, IDictionary <int, CompressedFeatureVector> > pair in allExamples)
{
if (i++ > numTrainingExamples)
{
stopTraining = true;
break;
}
if (i % 10000 == 0)
{
Redwood.Log("scoref-train", string.Format("On train example %d/%d = %.2f%%", i, numTrainingExamples, 100.0 * i / numTrainingExamples));
}
model.Learn(pair.first, pair.second, compressor);
}
}
Redwood.Log("scoref-train", "Writing models...");
model.WriteModel();
}
/// <exception cref="System.Exception"/>
public static void TrainRanking(PairwiseModel model)
{
Redwood.Log("scoref-train", "Reading compression...");
Compressor <string> compressor = IOUtils.ReadObjectFromFile(StatisticalCorefTrainer.compressorFile);
Redwood.Log("scoref-train", "Reading train data...");
IList <DocumentExamples> trainDocuments = IOUtils.ReadObjectFromFile(StatisticalCorefTrainer.extractedFeaturesFile);
Redwood.Log("scoref-train", "Training...");
for (int i = 0; i < model.GetNumEpochs(); i++)
{
Java.Util.Collections.Shuffle(trainDocuments);
int j = 0;
foreach (DocumentExamples doc in trainDocuments)
{
j++;
Redwood.Log("scoref-train", "On epoch: " + i + " / " + model.GetNumEpochs() + ", document: " + j + " / " + trainDocuments.Count);
IDictionary <int, IList <Example> > mentionToPotentialAntecedents = new Dictionary <int, IList <Example> >();
foreach (Example e in doc.examples)
{
int mention = e.mentionId2;
IList <Example> potentialAntecedents = mentionToPotentialAntecedents[mention];
if (potentialAntecedents == null)
{
potentialAntecedents = new List <Example>();
mentionToPotentialAntecedents[mention] = potentialAntecedents;
}
potentialAntecedents.Add(e);
}
IList <IList <Example> > examples = new List <IList <Example> >(mentionToPotentialAntecedents.Values);
Java.Util.Collections.Shuffle(examples);
foreach (IList <Example> es in examples)
{
if (es.Count == 0)
{
continue;
}
if (model is MaxMarginMentionRanker)
{
MaxMarginMentionRanker ranker = (MaxMarginMentionRanker)model;
bool noAntecedent = es.Stream().AllMatch(null);
es.Add(new Example(es[0], noAntecedent));
double maxPositiveScore = -double.MaxValue;
Example maxScoringPositive = null;
foreach (Example e_1 in es)
{
double score = model.Predict(e_1, doc.mentionFeatures, compressor);
if (e_1.label == 1)
{
System.Diagnostics.Debug.Assert((!noAntecedent ^ e_1.IsNewLink()));
if (score > maxPositiveScore)
{
maxPositiveScore = score;
maxScoringPositive = e_1;
}
}
}
System.Diagnostics.Debug.Assert((maxScoringPositive != null));
double maxNegativeScore = -double.MaxValue;
Example maxScoringNegative = null;
MaxMarginMentionRanker.ErrorType maxScoringEt = null;
foreach (Example e_2 in es)
{
double score = model.Predict(e_2, doc.mentionFeatures, compressor);
if (e_2.label != 1)
{
System.Diagnostics.Debug.Assert((!(noAntecedent && e_2.IsNewLink())));
MaxMarginMentionRanker.ErrorType et = MaxMarginMentionRanker.ErrorType.Wl;
if (noAntecedent && !e_2.IsNewLink())
{
et = MaxMarginMentionRanker.ErrorType.Fl;
}
else
{
if (!noAntecedent && e_2.IsNewLink())
{
if (e_2.mentionType2 == Dictionaries.MentionType.Pronominal)
{
et = MaxMarginMentionRanker.ErrorType.FnPron;
}
else
{
et = MaxMarginMentionRanker.ErrorType.Fn;
}
}
}
if (ranker.multiplicativeCost)
{
score = ranker.costs[et.id] * (1 - maxPositiveScore + score);
}
else
{
score += ranker.costs[et.id];
}
if (score > maxNegativeScore)
{
maxNegativeScore = score;
maxScoringNegative = e_2;
maxScoringEt = et;
}
}
}
System.Diagnostics.Debug.Assert((maxScoringNegative != null));
ranker.Learn(maxScoringPositive, maxScoringNegative, doc.mentionFeatures, compressor, maxScoringEt);
}
else
{
double maxPositiveScore = -double.MaxValue;
double maxNegativeScore = -double.MaxValue;
Example maxScoringPositive = null;
Example maxScoringNegative = null;
foreach (Example e_1 in es)
{
double score = model.Predict(e_1, doc.mentionFeatures, compressor);
if (e_1.label == 1)
{
if (score > maxPositiveScore)
{
maxPositiveScore = score;
maxScoringPositive = e_1;
}
}
else
{
if (score > maxNegativeScore)
{
maxNegativeScore = score;
maxScoringNegative = e_1;
}
}
}
model.Learn(maxScoringPositive, maxScoringNegative, doc.mentionFeatures, compressor, 1);
}
}
}
}
Redwood.Log("scoref-train", "Writing models...");
model.WriteModel();
}
