/// <summary>
/// Trains a batch of trees and returns the following: a list of
/// Update objects, the number of transitions correct, and the number
/// of transitions wrong.
/// </summary>
/// <remarks>
/// Trains a batch of trees and returns the following: a list of
/// Update objects, the number of transitions correct, and the number
/// of transitions wrong.
/// If the model is trained with multiple threads, it is expected
/// that a valid MulticoreWrapper is passed in which does the
/// processing. In that case, the processing is done on all of the
/// trees without updating any weights, which allows the results for
/// multithreaded training to be reproduced.
/// </remarks>
private Triple <IList <PerceptronModel.Update>, int, int> TrainBatch(IList <int> indices, IList <Tree> binarizedTrees, IList <IList <ITransition> > transitionLists, IList <PerceptronModel.Update> updates, Oracle oracle, MulticoreWrapper <int, Pair <int
, int> > wrapper)
{
int numCorrect = 0;
int numWrong = 0;
if (op.trainOptions.trainingThreads == 1)
{
foreach (int index in indices)
{
Pair <int, int> count = TrainTree(index, binarizedTrees, transitionLists, updates, oracle);
numCorrect += count.first;
numWrong += count.second;
}
}
else
{
foreach (int index in indices)
{
wrapper.Put(index);
}
wrapper.Join(false);
while (wrapper.Peek())
{
Pair <int, int> result = wrapper.Poll();
numCorrect += result.first;
numWrong += result.second;
}
}
return(new Triple <IList <PerceptronModel.Update>, int, int>(updates, numCorrect, numWrong));
}
public virtual void Annotate(Annotation annotation)
{
// turn the annotation into a sentence
if (annotation.ContainsKey(typeof(CoreAnnotations.SentencesAnnotation)))
{
if (nThreads == 1)
{
foreach (ICoreMap sentence in annotation.Get(typeof(CoreAnnotations.SentencesAnnotation)))
{
DoOneSentence(sentence);
}
}
else
{
MulticoreWrapper <ICoreMap, ICoreMap> wrapper = new MulticoreWrapper <ICoreMap, ICoreMap>(nThreads, new POSTaggerAnnotator.POSTaggerProcessor(this));
foreach (ICoreMap sentence in annotation.Get(typeof(CoreAnnotations.SentencesAnnotation)))
{
wrapper.Put(sentence);
while (wrapper.Peek())
{
wrapper.Poll();
}
}
wrapper.Join();
while (wrapper.Peek())
{
wrapper.Poll();
}
}
}
else
{
throw new Exception("unable to find words/tokens in: " + annotation);
}
}
/// <summary>
/// Fix tree structure, phrasal categories and part-of-speech labels in newly expanded
/// multi-word tokens.
/// </summary>
/// <exception cref="System.Exception"/>
/// <exception cref="Java.Util.Concurrent.ExecutionException"/>
private IList <Tree> FixMultiWordTokens(IList <Tree> trees)
{
bool ner = PropertiesUtils.GetBool(options, "ner", false);
// Shared resources
IFactory <TreeNormalizer> tnf = new _IFactory_389();
ITreeFactory tf = new LabeledScoredTreeFactory();
IThreadsafeProcessor <ICollection <Tree>, ICollection <Tree> > processor = new AnCoraProcessor.MultiWordProcessor(this, tnf, tf, ner);
int availableProcessors = Runtime.GetRuntime().AvailableProcessors();
MulticoreWrapper <ICollection <Tree>, ICollection <Tree> > wrapper = new MulticoreWrapper <ICollection <Tree>, ICollection <Tree> >(availableProcessors, processor, false);
// Chunk our work so that parallelization is actually worth it
int numChunks = availableProcessors * 20;
IList <IList <Tree> > chunked = CollectionUtils.PartitionIntoFolds(trees, numChunks);
IList <Tree> ret = new List <Tree>();
foreach (ICollection <Tree> coll in chunked)
{
wrapper.Put(coll);
while (wrapper.Peek())
{
Sharpen.Collections.AddAll(ret, wrapper.Poll());
}
}
wrapper.Join();
while (wrapper.Peek())
{
Sharpen.Collections.AddAll(ret, wrapper.Poll());
}
return(ret);
}
/// <summary>
/// Determine the total cost on the dataset associated with this
/// classifier using the current learned parameters.
/// </summary>
/// <remarks>
/// Determine the total cost on the dataset associated with this
/// classifier using the current learned parameters. This cost is
/// evaluated using mini-batch adaptive gradient descent.
/// This method launches multiple threads, each of which evaluates
/// training cost on a partition of the mini-batch.
/// </remarks>
/// <param name="batchSize"/>
/// <param name="regParameter">Regularization parameter (lambda)</param>
/// <param name="dropOutProb">
/// Drop-out probability. Hidden-layer units in the
/// neural network will be randomly turned off
/// while training a particular example with this
/// probability.
/// </param>
/// <returns>
/// A
/// <see cref="Cost"/>
/// object which describes the total cost of the given
/// weights, and includes gradients to be used for further
/// training
/// </returns>
public virtual Classifier.Cost ComputeCostFunction(int batchSize, double regParameter, double dropOutProb)
{
ValidateTraining();
IList <Example> examples = Edu.Stanford.Nlp.Parser.Nndep.Util.GetRandomSubList(dataset.examples, batchSize);
// Redo precomputations for only those features which are triggered
// by examples in this mini-batch.
ICollection <int> toPreCompute = GetToPreCompute(examples);
PreCompute(toPreCompute);
// Set up parameters for feedforward
Classifier.FeedforwardParams @params = new Classifier.FeedforwardParams(batchSize, dropOutProb);
// Zero out saved-embedding gradients
gradSaved = new double[][] { };
int numChunks = config.trainingThreads;
IList <IList <Example> > chunks = CollectionUtils.PartitionIntoFolds(examples, numChunks);
// Submit chunks for processing on separate threads
foreach (ICollection <Example> chunk in chunks)
{
jobHandler.Put(new Pair <ICollection <Example>, Classifier.FeedforwardParams>(chunk, @params));
}
jobHandler.Join(false);
// Join costs from each chunk
Classifier.Cost cost = null;
while (jobHandler.Peek())
{
Classifier.Cost otherCost = jobHandler.Poll();
if (cost == null)
{
cost = otherCost;
}
else
{
cost.Merge(otherCost);
}
}
if (cost == null)
{
return(null);
}
// Backpropagate gradients on saved pre-computed values to actual
// embeddings
cost.BackpropSaved(toPreCompute);
cost.AddL2Regularization(regParameter);
return(cost);
}
protected internal override void Calculate(double[] theta)
{
model.VectorToParams(theta);
SentimentCostAndGradient.ModelDerivatives derivatives;
if (model.op.trainOptions.nThreads == 1)
{
derivatives = ScoreDerivatives(trainingBatch);
}
else
{
// TODO: because some addition operations happen in different
// orders now, this results in slightly different values, which
// over time add up to significantly different models even when
// given the same random seed. Probably not a big deal.
// To be more specific, for trees T1, T2, T3, ... Tn,
// when using one thread, we sum the derivatives T1 + T2 ...
// When using multiple threads, we first sum T1 + ... + Tk,
// then sum Tk+1 + ... + T2k, etc, for split size k.
// The splits are then summed in order.
// This different sum order results in slightly different numbers.
MulticoreWrapper <IList <Tree>, SentimentCostAndGradient.ModelDerivatives> wrapper = new MulticoreWrapper <IList <Tree>, SentimentCostAndGradient.ModelDerivatives>(model.op.trainOptions.nThreads, new SentimentCostAndGradient.ScoringProcessor(this
));
// use wrapper.nThreads in case the number of threads was automatically changed
foreach (IList <Tree> chunk in CollectionUtils.PartitionIntoFolds(trainingBatch, wrapper.NThreads()))
{
wrapper.Put(chunk);
}
wrapper.Join();
derivatives = new SentimentCostAndGradient.ModelDerivatives(model);
while (wrapper.Peek())
{
SentimentCostAndGradient.ModelDerivatives batchDerivatives = wrapper.Poll();
derivatives.Add(batchDerivatives);
}
}
// scale the error by the number of sentences so that the
// regularization isn't drowned out for large training batchs
double scale = (1.0 / trainingBatch.Count);
value = derivatives.error * scale;
value += ScaleAndRegularize(derivatives.binaryTD, model.binaryTransform, scale, model.op.trainOptions.regTransformMatrix, false);
value += ScaleAndRegularize(derivatives.binaryCD, model.binaryClassification, scale, model.op.trainOptions.regClassification, true);
value += ScaleAndRegularizeTensor(derivatives.binaryTensorTD, model.binaryTensors, scale, model.op.trainOptions.regTransformTensor);
value += ScaleAndRegularize(derivatives.unaryCD, model.unaryClassification, scale, model.op.trainOptions.regClassification, false, true);
value += ScaleAndRegularize(derivatives.wordVectorD, model.wordVectors, scale, model.op.trainOptions.regWordVector, true, false);
derivative = NeuralUtils.ParamsToVector(theta.Length, derivatives.binaryTD.ValueIterator(), derivatives.binaryCD.ValueIterator(), SimpleTensor.IteratorSimpleMatrix(derivatives.binaryTensorTD.ValueIterator()), derivatives.unaryCD.Values.GetEnumerator
(), derivatives.wordVectorD.Values.GetEnumerator());
}
public static void RedoTags(IList <Tree> trees, Edu.Stanford.Nlp.Tagger.Common.Tagger tagger, int nThreads)
{
if (nThreads == 1)
{
foreach (Tree tree in trees)
{
RedoTags(tree, tagger);
}
}
else
{
MulticoreWrapper <Tree, Tree> wrapper = new MulticoreWrapper <Tree, Tree>(nThreads, new ShiftReduceParser.RetagProcessor(tagger));
foreach (Tree tree in trees)
{
wrapper.Put(tree);
}
wrapper.Join();
}
}
public static IdentityHashMap <Tree, IList <Tree> > ConvertToTrees(ICollection <Tree> keys, IdentityHashMap <Tree, byte[]> compressed, int numThreads)
{
IdentityHashMap <Tree, IList <Tree> > uncompressed = Generics.NewIdentityHashMap();
MulticoreWrapper <byte[], IList <Tree> > wrapper = new MulticoreWrapper <byte[], IList <Tree> >(numThreads, new CacheParseHypotheses.DecompressionProcessor());
foreach (Tree tree in keys)
{
wrapper.Put(compressed[tree]);
}
foreach (Tree tree_1 in keys)
{
if (!wrapper.Peek())
{
wrapper.Join();
}
uncompressed[tree_1] = wrapper.Poll();
}
return(uncompressed);
}
/// <summary>Segment input and write to output stream.</summary>
/// <param name="segmenter"/>
/// <param name="br"/>
/// <param name="pwOut"/>
/// <param name="nThreads"/>
/// <returns>input characters processed per second</returns>
private static double Decode(Edu.Stanford.Nlp.International.Arabic.Process.ArabicSegmenter segmenter, BufferedReader br, PrintWriter pwOut, int nThreads)
{
System.Diagnostics.Debug.Assert(nThreads > 0);
long nChars = 0;
long startTime = Runtime.NanoTime();
if (nThreads > 1)
{
MulticoreWrapper <string, string> wrapper = new MulticoreWrapper <string, string>(nThreads, segmenter);
try
{
for (string line; (line = br.ReadLine()) != null;)
{
nChars += line.Length;
wrapper.Put(line);
while (wrapper.Peek())
{
pwOut.Println(wrapper.Poll());
}
}
wrapper.Join();
while (wrapper.Peek())
{
pwOut.Println(wrapper.Poll());
}
}
catch (IOException e)
{
log.Warn(e);
}
}
else
{
nChars = segmenter.Segment(br, pwOut);
}
long duration = Runtime.NanoTime() - startTime;
double charsPerSec = (double)nChars / (duration / 1000000000.0);
return(charsPerSec);
}
// static main
/// <param name="args">Command-line arguments: modelFile (runs as a filter from stdin to stdout)</param>
public static void Main(string[] args)
{
if (args.Length != 1)
{
System.Console.Error.Printf("Usage: java %s model_file < input_file%n", typeof(Edu.Stanford.Nlp.Tagger.Maxent.Documentation.MulticoreWrapperDemo).FullName);
System.Environment.Exit(-1);
}
try
{
// Load MaxentTagger, which is threadsafe
string modelFile = args[0];
MaxentTagger tagger = new MaxentTagger(modelFile);
// Configure to run with 4 worker threads
int nThreads = 4;
MulticoreWrapper <string, string> wrapper = new MulticoreWrapper <string, string>(nThreads, new _IThreadsafeProcessor_42(tagger));
// MaxentTagger is threadsafe
// Submit jobs, which come from stdin
BufferedReader br = new BufferedReader(new InputStreamReader(Runtime.@in));
for (string line; (line = br.ReadLine()) != null;)
{
wrapper.Put(line);
while (wrapper.Peek())
{
System.Console.Out.WriteLine(wrapper.Poll());
}
}
// Finished reading the input. Wait for jobs to finish
wrapper.Join();
while (wrapper.Peek())
{
System.Console.Out.WriteLine(wrapper.Poll());
}
}
catch (IOException e)
{
Sharpen.Runtime.PrintStackTrace(e);
}
}
/// <summary>
/// Samples the complete sequence once in the forward direction
/// Destructively modifies the sequence in place.
/// </summary>
/// <param name="sequence">the sequence to start with.</param>
public virtual double SampleSequenceForward(ISequenceModel model, int[] sequence, double temperature, ICollection <int> onlySampleThesePositions)
{
double returnScore = double.NegativeInfinity;
// log.info("Sampling forward");
if (onlySampleThesePositions != null)
{
foreach (int pos in onlySampleThesePositions)
{
returnScore = SamplePosition(model, sequence, pos, temperature);
}
}
else
{
if (samplingStyle == SequentialSampling)
{
for (int pos = 0; pos < sequence.Length; pos++)
{
returnScore = SamplePosition(model, sequence, pos, temperature);
}
}
else
{
if (samplingStyle == RandomSampling)
{
foreach (int aSequence in sequence)
{
int pos = random.NextInt(sequence.Length);
returnScore = SamplePosition(model, sequence, pos, temperature);
}
}
else
{
if (samplingStyle == ChromaticSampling)
{
// make copies of the sequences and merge at the end
IList <Pair <int, int> > results = new List <Pair <int, int> >();
foreach (IList <int> indieList in partition)
{
if (indieList.Count <= chromaticSize)
{
foreach (int pos in indieList)
{
Pair <int, double> newPosProb = SamplePositionHelper(model, sequence, pos, temperature);
sequence[pos] = newPosProb.First();
}
}
else
{
MulticoreWrapper <IList <int>, IList <Pair <int, int> > > wrapper = new MulticoreWrapper <IList <int>, IList <Pair <int, int> > >(chromaticSize, new _IThreadsafeProcessor_269(this, model, sequence, temperature));
// returns the position to sample in first place and new label in second place
results.Clear();
int interval = System.Math.Max(1, indieList.Count / chromaticSize);
for (int begin = 0; end < indieListSize; begin += interval)
{
end = System.Math.Min(begin + interval, indieListSize);
wrapper.Put(indieList.SubList(begin, end));
while (wrapper.Peek())
{
Sharpen.Collections.AddAll(results, wrapper.Poll());
}
}
wrapper.Join();
while (wrapper.Peek())
{
Sharpen.Collections.AddAll(results, wrapper.Poll());
}
foreach (Pair <int, int> posVal in results)
{
sequence[posVal.First()] = posVal.Second();
}
}
}
returnScore = model.ScoreOf(sequence);
}
}
}
}
return(returnScore);
}
/// <summary>Test the parser on a treebank.</summary>
/// <remarks>
/// Test the parser on a treebank. Parses will be written to stdout, and
/// various other information will be written to stderr and stdout,
/// particularly if <code>op.testOptions.verbose</code> is true.
/// </remarks>
/// <param name="testTreebank">The treebank to parse</param>
/// <returns>
/// The labeled precision/recall F<sub>1</sub> (EVALB measure)
/// of the parser on the treebank.
/// </returns>
public virtual double TestOnTreebank(Treebank testTreebank)
{
log.Info("Testing on treebank");
Timing treebankTotalTimer = new Timing();
TreePrint treePrint = op.testOptions.TreePrint(op.tlpParams);
ITreebankLangParserParams tlpParams = op.tlpParams;
ITreebankLanguagePack tlp = op.Langpack();
PrintWriter pwOut;
PrintWriter pwErr;
if (op.testOptions.quietEvaluation)
{
NullOutputStream quiet = new NullOutputStream();
pwOut = tlpParams.Pw(quiet);
pwErr = tlpParams.Pw(quiet);
}
else
{
pwOut = tlpParams.Pw();
pwErr = tlpParams.Pw(System.Console.Error);
}
if (op.testOptions.verbose)
{
pwErr.Print("Testing ");
pwErr.Println(testTreebank.TextualSummary(tlp));
}
if (op.testOptions.evalb)
{
EvalbFormatWriter.InitEVALBfiles(tlpParams);
}
PrintWriter pwFileOut = null;
if (op.testOptions.writeOutputFiles)
{
string fname = op.testOptions.outputFilesPrefix + "." + op.testOptions.outputFilesExtension;
try
{
pwFileOut = op.tlpParams.Pw(new FileOutputStream(fname));
}
catch (IOException ioe)
{
Sharpen.Runtime.PrintStackTrace(ioe);
}
}
PrintWriter pwStats = null;
if (op.testOptions.outputkBestEquivocation != null)
{
try
{
pwStats = op.tlpParams.Pw(new FileOutputStream(op.testOptions.outputkBestEquivocation));
}
catch (IOException ioe)
{
Sharpen.Runtime.PrintStackTrace(ioe);
}
}
if (op.testOptions.testingThreads != 1)
{
MulticoreWrapper <IList <IHasWord>, IParserQuery> wrapper = new MulticoreWrapper <IList <IHasWord>, IParserQuery>(op.testOptions.testingThreads, new ParsingThreadsafeProcessor(pqFactory, pwErr));
LinkedList <Tree> goldTrees = new LinkedList <Tree>();
foreach (Tree goldTree in testTreebank)
{
IList <IHasWord> sentence = GetInputSentence(goldTree);
goldTrees.Add(goldTree);
pwErr.Println("Parsing [len. " + sentence.Count + "]: " + SentenceUtils.ListToString(sentence));
wrapper.Put(sentence);
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
goldTree = goldTrees.Poll();
ProcessResults(pq, goldTree, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
// for tree iterator
wrapper.Join();
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
Tree goldTree_1 = goldTrees.Poll();
ProcessResults(pq, goldTree_1, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
else
{
IParserQuery pq = pqFactory.ParserQuery();
foreach (Tree goldTree in testTreebank)
{
IList <CoreLabel> sentence = GetInputSentence(goldTree);
pwErr.Println("Parsing [len. " + sentence.Count + "]: " + SentenceUtils.ListToString(sentence));
pq.ParseAndReport(sentence, pwErr);
ProcessResults(pq, goldTree, pwErr, pwOut, pwFileOut, pwStats, treePrint);
}
}
// for tree iterator
//Done parsing...print the results of the evaluations
treebankTotalTimer.Done("Testing on treebank");
if (op.testOptions.quietEvaluation)
{
pwErr = tlpParams.Pw(System.Console.Error);
}
if (saidMemMessage)
{
ParserUtils.PrintOutOfMemory(pwErr);
}
if (op.testOptions.evalb)
{
EvalbFormatWriter.CloseEVALBfiles();
}
if (numSkippedEvals != 0)
{
pwErr.Printf("Unable to evaluate %d parser hypotheses due to yield mismatch\n", numSkippedEvals);
}
// only created here so we know what parser types are supported...
IParserQuery pq_1 = pqFactory.ParserQuery();
if (summary)
{
if (pcfgLB != null)
{
pcfgLB.Display(false, pwErr);
}
if (pcfgChildSpecific != null)
{
pcfgChildSpecific.Display(false, pwErr);
}
if (pcfgLA != null)
{
pcfgLA.Display(false, pwErr);
}
if (pcfgCB != null)
{
pcfgCB.Display(false, pwErr);
}
if (pcfgDA != null)
{
pcfgDA.Display(false, pwErr);
}
if (pcfgTA != null)
{
pcfgTA.Display(false, pwErr);
}
if (pcfgLL != null && pq_1.GetPCFGParser() != null)
{
pcfgLL.Display(false, pwErr);
}
if (depDA != null)
{
depDA.Display(false, pwErr);
}
if (depTA != null)
{
depTA.Display(false, pwErr);
}
if (depLL != null && pq_1.GetDependencyParser() != null)
{
depLL.Display(false, pwErr);
}
if (factLB != null)
{
factLB.Display(false, pwErr);
}
if (factChildSpecific != null)
{
factChildSpecific.Display(false, pwErr);
}
if (factLA != null)
{
factLA.Display(false, pwErr);
}
if (factCB != null)
{
factCB.Display(false, pwErr);
}
if (factDA != null)
{
factDA.Display(false, pwErr);
}
if (factTA != null)
{
factTA.Display(false, pwErr);
}
if (factLL != null && pq_1.GetFactoredParser() != null)
{
factLL.Display(false, pwErr);
}
if (pcfgCatE != null)
{
pcfgCatE.Display(false, pwErr);
}
foreach (IEval eval in evals)
{
eval.Display(false, pwErr);
}
foreach (BestOfTopKEval eval_1 in topKEvals)
{
eval_1.Display(false, pwErr);
}
}
// these ones only have a display mode, so display if turned on!!
if (pcfgRUO != null)
{
pcfgRUO.Display(true, pwErr);
}
if (pcfgCUO != null)
{
pcfgCUO.Display(true, pwErr);
}
if (tsv)
{
NumberFormat nf = new DecimalFormat("0.00");
pwErr.Println("factF1\tfactDA\tfactEx\tpcfgF1\tdepDA\tfactTA\tnum");
if (factLB != null)
{
pwErr.Print(nf.Format(factLB.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetDependencyParser() != null && factDA != null)
{
pwErr.Print(nf.Format(factDA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (factLB != null)
{
pwErr.Print(nf.Format(factLB.GetExactPercent()));
}
pwErr.Print("\t");
if (pcfgLB != null)
{
pwErr.Print(nf.Format(pcfgLB.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetDependencyParser() != null && depDA != null)
{
pwErr.Print(nf.Format(depDA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (pq_1.GetPCFGParser() != null && factTA != null)
{
pwErr.Print(nf.Format(factTA.GetEvalbF1Percent()));
}
pwErr.Print("\t");
if (factLB != null)
{
pwErr.Print(factLB.GetNum());
}
pwErr.Println();
}
double f1 = 0.0;
if (factLB != null)
{
f1 = factLB.GetEvalbF1();
}
//Close files (if necessary)
if (pwFileOut != null)
{
pwFileOut.Close();
}
if (pwStats != null)
{
pwStats.Close();
}
if (parserQueryEvals != null)
{
foreach (IParserQueryEval parserQueryEval in parserQueryEvals)
{
parserQueryEval.Display(false, pwErr);
}
}
return(f1);
}
// fill value & derivative
protected internal override void Calculate(double[] theta)
{
dvModel.VectorToParams(theta);
double localValue = 0.0;
double[] localDerivative = new double[theta.Length];
TwoDimensionalMap <string, string, SimpleMatrix> binaryW_dfsG;
TwoDimensionalMap <string, string, SimpleMatrix> binaryW_dfsB;
binaryW_dfsG = TwoDimensionalMap.TreeMap();
binaryW_dfsB = TwoDimensionalMap.TreeMap();
TwoDimensionalMap <string, string, SimpleMatrix> binaryScoreDerivativesG;
TwoDimensionalMap <string, string, SimpleMatrix> binaryScoreDerivativesB;
binaryScoreDerivativesG = TwoDimensionalMap.TreeMap();
binaryScoreDerivativesB = TwoDimensionalMap.TreeMap();
IDictionary <string, SimpleMatrix> unaryW_dfsG;
IDictionary <string, SimpleMatrix> unaryW_dfsB;
unaryW_dfsG = new SortedDictionary <string, SimpleMatrix>();
unaryW_dfsB = new SortedDictionary <string, SimpleMatrix>();
IDictionary <string, SimpleMatrix> unaryScoreDerivativesG;
IDictionary <string, SimpleMatrix> unaryScoreDerivativesB;
unaryScoreDerivativesG = new SortedDictionary <string, SimpleMatrix>();
unaryScoreDerivativesB = new SortedDictionary <string, SimpleMatrix>();
IDictionary <string, SimpleMatrix> wordVectorDerivativesG = new SortedDictionary <string, SimpleMatrix>();
IDictionary <string, SimpleMatrix> wordVectorDerivativesB = new SortedDictionary <string, SimpleMatrix>();
foreach (TwoDimensionalMap.Entry <string, string, SimpleMatrix> entry in dvModel.binaryTransform)
{
int numRows = entry.GetValue().NumRows();
int numCols = entry.GetValue().NumCols();
binaryW_dfsG.Put(entry.GetFirstKey(), entry.GetSecondKey(), new SimpleMatrix(numRows, numCols));
binaryW_dfsB.Put(entry.GetFirstKey(), entry.GetSecondKey(), new SimpleMatrix(numRows, numCols));
binaryScoreDerivativesG.Put(entry.GetFirstKey(), entry.GetSecondKey(), new SimpleMatrix(1, numRows));
binaryScoreDerivativesB.Put(entry.GetFirstKey(), entry.GetSecondKey(), new SimpleMatrix(1, numRows));
}
foreach (KeyValuePair <string, SimpleMatrix> entry_1 in dvModel.unaryTransform)
{
int numRows = entry_1.Value.NumRows();
int numCols = entry_1.Value.NumCols();
unaryW_dfsG[entry_1.Key] = new SimpleMatrix(numRows, numCols);
unaryW_dfsB[entry_1.Key] = new SimpleMatrix(numRows, numCols);
unaryScoreDerivativesG[entry_1.Key] = new SimpleMatrix(1, numRows);
unaryScoreDerivativesB[entry_1.Key] = new SimpleMatrix(1, numRows);
}
if (op.trainOptions.trainWordVectors)
{
foreach (KeyValuePair <string, SimpleMatrix> entry_2 in dvModel.wordVectors)
{
int numRows = entry_2.Value.NumRows();
int numCols = entry_2.Value.NumCols();
wordVectorDerivativesG[entry_2.Key] = new SimpleMatrix(numRows, numCols);
wordVectorDerivativesB[entry_2.Key] = new SimpleMatrix(numRows, numCols);
}
}
// Some optimization methods prints out a line without an end, so our
// debugging statements are misaligned
Timing scoreTiming = new Timing();
scoreTiming.Doing("Scoring trees");
int treeNum = 0;
MulticoreWrapper <Tree, Pair <DeepTree, DeepTree> > wrapper = new MulticoreWrapper <Tree, Pair <DeepTree, DeepTree> >(op.trainOptions.trainingThreads, new DVParserCostAndGradient.ScoringProcessor(this));
foreach (Tree tree in trainingBatch)
{
wrapper.Put(tree);
}
wrapper.Join();
scoreTiming.Done();
while (wrapper.Peek())
{
Pair <DeepTree, DeepTree> result = wrapper.Poll();
DeepTree goldTree = result.first;
DeepTree bestTree = result.second;
StringBuilder treeDebugLine = new StringBuilder();
Formatter formatter = new Formatter(treeDebugLine);
bool isDone = (Math.Abs(bestTree.GetScore() - goldTree.GetScore()) <= 0.00001 || goldTree.GetScore() > bestTree.GetScore());
string done = isDone ? "done" : string.Empty;
formatter.Format("Tree %6d Highest tree: %12.4f Correct tree: %12.4f %s", treeNum, bestTree.GetScore(), goldTree.GetScore(), done);
log.Info(treeDebugLine.ToString());
if (!isDone)
{
// if the gold tree is better than the best hypothesis tree by
// a large enough margin, then the score difference will be 0
// and we ignore the tree
double valueDelta = bestTree.GetScore() - goldTree.GetScore();
//double valueDelta = Math.max(0.0, - scoreGold + bestScore);
localValue += valueDelta;
// get the context words for this tree - should be the same
// for either goldTree or bestTree
IList <string> words = GetContextWords(goldTree.GetTree());
// The derivatives affected by this tree are only based on the
// nodes present in this tree, eg not all matrix derivatives
// will be affected by this tree
BackpropDerivative(goldTree.GetTree(), words, goldTree.GetVectors(), binaryW_dfsG, unaryW_dfsG, binaryScoreDerivativesG, unaryScoreDerivativesG, wordVectorDerivativesG);
BackpropDerivative(bestTree.GetTree(), words, bestTree.GetVectors(), binaryW_dfsB, unaryW_dfsB, binaryScoreDerivativesB, unaryScoreDerivativesB, wordVectorDerivativesB);
}
++treeNum;
}
double[] localDerivativeGood;
double[] localDerivativeB;
if (op.trainOptions.trainWordVectors)
{
localDerivativeGood = NeuralUtils.ParamsToVector(theta.Length, binaryW_dfsG.ValueIterator(), unaryW_dfsG.Values.GetEnumerator(), binaryScoreDerivativesG.ValueIterator(), unaryScoreDerivativesG.Values.GetEnumerator(), wordVectorDerivativesG.Values
.GetEnumerator());
localDerivativeB = NeuralUtils.ParamsToVector(theta.Length, binaryW_dfsB.ValueIterator(), unaryW_dfsB.Values.GetEnumerator(), binaryScoreDerivativesB.ValueIterator(), unaryScoreDerivativesB.Values.GetEnumerator(), wordVectorDerivativesB.Values
.GetEnumerator());
}
else
{
localDerivativeGood = NeuralUtils.ParamsToVector(theta.Length, binaryW_dfsG.ValueIterator(), unaryW_dfsG.Values.GetEnumerator(), binaryScoreDerivativesG.ValueIterator(), unaryScoreDerivativesG.Values.GetEnumerator());
localDerivativeB = NeuralUtils.ParamsToVector(theta.Length, binaryW_dfsB.ValueIterator(), unaryW_dfsB.Values.GetEnumerator(), binaryScoreDerivativesB.ValueIterator(), unaryScoreDerivativesB.Values.GetEnumerator());
}
// correct - highest
for (int i = 0; i < localDerivativeGood.Length; i++)
{
localDerivative[i] = localDerivativeB[i] - localDerivativeGood[i];
}
// TODO: this is where we would combine multiple costs if we had parallelized the calculation
value = localValue;
derivative = localDerivative;
// normalizing by training batch size
value = (1.0 / trainingBatch.Count) * value;
ArrayMath.MultiplyInPlace(derivative, (1.0 / trainingBatch.Count));
// add regularization to cost:
double[] currentParams = dvModel.ParamsToVector();
double regCost = 0;
foreach (double currentParam in currentParams)
{
regCost += currentParam * currentParam;
}
regCost = op.trainOptions.regCost * 0.5 * regCost;
value += regCost;
// add regularization to gradient
ArrayMath.MultiplyInPlace(currentParams, op.trainOptions.regCost);
ArrayMath.PairwiseAddInPlace(derivative, currentParams);
}
/// <summary>Calculates both value and partial derivatives at the point x, and save them internally.</summary>
protected internal override void Calculate(double[] x)
{
double prob = 0.0;
// the log prob of the sequence given the model, which is the negation of value at this point
// final double[][] weights = to2D(x);
To2D(x, weights);
SetWeights(weights);
// the expectations over counts
// first index is feature index, second index is of possible labeling
// double[][] E = empty2D();
Clear2D(E);
Clear2D(dropoutPriorGradTotal);
MulticoreWrapper <Pair <int, bool>, Quadruple <int, double, IDictionary <int, double[]>, IDictionary <int, double[]> > > wrapper = new MulticoreWrapper <Pair <int, bool>, Quadruple <int, double, IDictionary <int, double[]>, IDictionary <int, double[]> > >
(multiThreadGrad, dropoutPriorThreadProcessor);
// supervised part
for (int m = 0; m < totalData.Length; m++)
{
bool submitIsUnsup = (m >= unsupDropoutStartIndex);
wrapper.Put(new Pair <int, bool>(m, submitIsUnsup));
while (wrapper.Peek())
{
Quadruple <int, double, IDictionary <int, double[]>, IDictionary <int, double[]> > result = wrapper.Poll();
int docIndex = result.First();
bool isUnsup = docIndex >= unsupDropoutStartIndex;
if (isUnsup)
{
prob += unsupDropoutScale * result.Second();
}
else
{
prob += result.Second();
}
IDictionary <int, double[]> partialDropout = result.Fourth();
if (partialDropout != null)
{
if (isUnsup)
{
Combine2DArr(dropoutPriorGradTotal, partialDropout, unsupDropoutScale);
}
else
{
Combine2DArr(dropoutPriorGradTotal, partialDropout);
}
}
if (!isUnsup)
{
IDictionary <int, double[]> partialE = result.Third();
if (partialE != null)
{
Combine2DArr(E, partialE);
}
}
}
}
wrapper.Join();
while (wrapper.Peek())
{
Quadruple <int, double, IDictionary <int, double[]>, IDictionary <int, double[]> > result = wrapper.Poll();
int docIndex = result.First();
bool isUnsup = docIndex >= unsupDropoutStartIndex;
if (isUnsup)
{
prob += unsupDropoutScale * result.Second();
}
else
{
prob += result.Second();
}
IDictionary <int, double[]> partialDropout = result.Fourth();
if (partialDropout != null)
{
if (isUnsup)
{
Combine2DArr(dropoutPriorGradTotal, partialDropout, unsupDropoutScale);
}
else
{
Combine2DArr(dropoutPriorGradTotal, partialDropout);
}
}
if (!isUnsup)
{
IDictionary <int, double[]> partialE = result.Third();
if (partialE != null)
{
Combine2DArr(E, partialE);
}
}
}
if (double.IsNaN(prob))
{
// shouldn't be the case
throw new Exception("Got NaN for prob in CRFLogConditionalObjectiveFunctionWithDropout.calculate()" + " - this may well indicate numeric underflow due to overly long documents.");
}
// because we minimize -L(\theta)
value = -prob;
if (Verbose)
{
log.Info("value is " + System.Math.Exp(-value));
}
// compute the partial derivative for each feature by comparing expected counts to empirical counts
int index = 0;
for (int i = 0; i < E.Length; i++)
{
for (int j = 0; j < E[i].Length; j++)
{
// because we minimize -L(\theta)
derivative[index] = (E[i][j] - Ehat[i][j]);
derivative[index] += dropoutScale * dropoutPriorGradTotal[i][j];
if (Verbose)
{
log.Info("deriv(" + i + ',' + j + ") = " + E[i][j] + " - " + Ehat[i][j] + " = " + derivative[index]);
}
index++;
}
}
}
/// <summary>Test on a file containing correct tags already.</summary>
/// <remarks>
/// Test on a file containing correct tags already. when init'ing from trees
/// TODO: Add the ability to have a second transformer to transform output back; possibly combine this method
/// with method below
/// </remarks>
/// <exception cref="System.IO.IOException"/>
private void Test()
{
numSentences = 0;
confusionMatrix = new ConfusionMatrix <string>();
PrintFile pf = null;
PrintFile pf1 = null;
PrintFile pf3 = null;
if (writeWords)
{
pf = new PrintFile(saveRoot + ".words");
}
if (writeUnknDict)
{
pf1 = new PrintFile(saveRoot + ".un.dict");
}
if (writeTopWords)
{
pf3 = new PrintFile(saveRoot + ".words.top");
}
bool verboseResults = config.GetVerboseResults();
if (config.GetNThreads() != 1)
{
MulticoreWrapper <IList <TaggedWord>, TestSentence> wrapper = new MulticoreWrapper <IList <TaggedWord>, TestSentence>(config.GetNThreads(), new TestClassifier.TestSentenceProcessor(maxentTagger));
foreach (IList <TaggedWord> taggedSentence in fileRecord.Reader())
{
wrapper.Put(taggedSentence);
while (wrapper.Peek())
{
ProcessResults(wrapper.Poll(), pf, pf1, pf3, verboseResults);
}
}
wrapper.Join();
while (wrapper.Peek())
{
ProcessResults(wrapper.Poll(), pf, pf1, pf3, verboseResults);
}
}
else
{
foreach (IList <TaggedWord> taggedSentence in fileRecord.Reader())
{
TestSentence testS = new TestSentence(maxentTagger);
testS.SetCorrectTags(taggedSentence);
testS.TagSentence(taggedSentence, false);
ProcessResults(testS, pf, pf1, pf3, verboseResults);
}
}
if (pf != null)
{
pf.Close();
}
if (pf1 != null)
{
pf1.Close();
}
if (pf3 != null)
{
pf3.Close();
}
}
protected internal virtual double MultiThreadGradient(IList <int> docIDs, bool calculateEmpirical)
{
double objective = 0.0;
// TODO: This is a bunch of unnecessary heap traffic, should all be on the stack
if (multiThreadGrad > 1)
{
if (parallelE == null)
{
parallelE = new double[multiThreadGrad][][];
for (int i = 0; i < multiThreadGrad; i++)
{
parallelE[i] = Empty2D();
}
}
if (calculateEmpirical)
{
if (parallelEhat == null)
{
parallelEhat = new double[multiThreadGrad][][];
for (int i = 0; i < multiThreadGrad; i++)
{
parallelEhat[i] = Empty2D();
}
}
}
}
// TODO: this is a huge amount of machinery for no discernible reason
MulticoreWrapper <Pair <int, IList <int> >, Pair <int, double> > wrapper = new MulticoreWrapper <Pair <int, IList <int> >, Pair <int, double> >(multiThreadGrad, (calculateEmpirical ? expectedAndEmpiricalThreadProcessor : expectedThreadProcessor));
int totalLen = docIDs.Count;
int partLen = totalLen / multiThreadGrad;
int currIndex = 0;
for (int part = 0; part < multiThreadGrad; part++)
{
int endIndex = currIndex + partLen;
if (part == multiThreadGrad - 1)
{
endIndex = totalLen;
}
// TODO: let's not construct a sub-list of DocIDs, unnecessary object creation, can calculate directly from ThreadID
IList <int> subList = docIDs.SubList(currIndex, endIndex);
wrapper.Put(new Pair <int, IList <int> >(part, subList));
currIndex = endIndex;
}
wrapper.Join();
// This all seems fine. May want to start running this after the joins, in case we have different end-times
while (wrapper.Peek())
{
Pair <int, double> result = wrapper.Poll();
int tID = result.First();
objective += result.Second();
if (multiThreadGrad > 1)
{
Combine2DArr(E, parallelE[tID]);
if (calculateEmpirical)
{
Combine2DArr(Ehat, parallelEhat[tID]);
}
}
}
return(objective);
}
public virtual void ParseFiles <_T0>(string[] args, int argIndex, bool tokenized, ITokenizerFactory <_T0> tokenizerFactory, string elementDelimiter, string sentenceDelimiter, IFunction <IList <IHasWord>, IList <IHasWord> > escaper, string tagDelimiter
)
where _T0 : IHasWord
{
DocumentPreprocessor.DocType docType = (elementDelimiter == null) ? DocumentPreprocessor.DocType.Plain : DocumentPreprocessor.DocType.Xml;
if (op.testOptions.verbose)
{
if (tokenizerFactory != null)
{
pwErr.Println("parseFiles: Tokenizer factory is: " + tokenizerFactory);
}
}
Timing timer = new Timing();
// timer.start(); // constructor already starts it.
//Loop over the files
for (int i = argIndex; i < args.Length; i++)
{
string filename = args[i];
DocumentPreprocessor documentPreprocessor;
if (filename.Equals("-"))
{
try
{
documentPreprocessor = new DocumentPreprocessor(IOUtils.ReaderFromStdin(op.tlpParams.GetInputEncoding()), docType);
}
catch (IOException e)
{
throw new RuntimeIOException(e);
}
}
else
{
documentPreprocessor = new DocumentPreprocessor(filename, docType, op.tlpParams.GetInputEncoding());
}
//Unused values are null per the main() method invocation below
//null is the default for these properties
documentPreprocessor.SetSentenceFinalPuncWords(tlp.SentenceFinalPunctuationWords());
documentPreprocessor.SetEscaper(escaper);
documentPreprocessor.SetSentenceDelimiter(sentenceDelimiter);
documentPreprocessor.SetTagDelimiter(tagDelimiter);
documentPreprocessor.SetElementDelimiter(elementDelimiter);
if (tokenizerFactory == null)
{
documentPreprocessor.SetTokenizerFactory((tokenized) ? null : tlp.GetTokenizerFactory());
}
else
{
documentPreprocessor.SetTokenizerFactory(tokenizerFactory);
}
//Setup the output
PrintWriter pwo = pwOut;
if (op.testOptions.writeOutputFiles)
{
string normalizedName = filename;
try
{
new URL(normalizedName);
// this will exception if not a URL
normalizedName = normalizedName.ReplaceAll("/", "_");
}
catch (MalformedURLException)
{
}
//It isn't a URL, so silently ignore
string ext = (op.testOptions.outputFilesExtension == null) ? "stp" : op.testOptions.outputFilesExtension;
string fname = normalizedName + '.' + ext;
if (op.testOptions.outputFilesDirectory != null && !op.testOptions.outputFilesDirectory.IsEmpty())
{
string fseparator = Runtime.GetProperty("file.separator");
if (fseparator == null || fseparator.IsEmpty())
{
fseparator = "/";
}
File fnameFile = new File(fname);
fname = op.testOptions.outputFilesDirectory + fseparator + fnameFile.GetName();
}
try
{
pwo = op.tlpParams.Pw(new FileOutputStream(fname));
}
catch (IOException ioe)
{
throw new RuntimeIOException(ioe);
}
}
treePrint.PrintHeader(pwo, op.tlpParams.GetOutputEncoding());
pwErr.Println("Parsing file: " + filename);
int num = 0;
int numProcessed = 0;
if (op.testOptions.testingThreads != 1)
{
MulticoreWrapper <IList <IHasWord>, IParserQuery> wrapper = new MulticoreWrapper <IList <IHasWord>, IParserQuery>(op.testOptions.testingThreads, new ParsingThreadsafeProcessor(pqFactory, pwErr));
foreach (IList <IHasWord> sentence in documentPreprocessor)
{
num++;
numSents++;
int len = sentence.Count;
numWords += len;
pwErr.Println("Parsing [sent. " + num + " len. " + len + "]: " + SentenceUtils.ListToString(sentence, true));
wrapper.Put(sentence);
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
ProcessResults(pq, numProcessed++, pwo);
}
}
wrapper.Join();
while (wrapper.Peek())
{
IParserQuery pq = wrapper.Poll();
ProcessResults(pq, numProcessed++, pwo);
}
}
else
{
IParserQuery pq = pqFactory.ParserQuery();
foreach (IList <IHasWord> sentence in documentPreprocessor)
{
num++;
numSents++;
int len = sentence.Count;
numWords += len;
pwErr.Println("Parsing [sent. " + num + " len. " + len + "]: " + SentenceUtils.ListToString(sentence, true));
pq.ParseAndReport(sentence, pwErr);
ProcessResults(pq, numProcessed++, pwo);
}
}
treePrint.PrintFooter(pwo);
if (op.testOptions.writeOutputFiles)
{
pwo.Close();
}
pwErr.Println("Parsed file: " + filename + " [" + num + " sentences].");
}
long millis = timer.Stop();
if (summary)
{
if (pcfgLL != null)
{
pcfgLL.Display(false, pwErr);
}
if (depLL != null)
{
depLL.Display(false, pwErr);
}
if (factLL != null)
{
factLL.Display(false, pwErr);
}
}
if (saidMemMessage)
{
ParserUtils.PrintOutOfMemory(pwErr);
}
double wordspersec = numWords / (((double)millis) / 1000);
double sentspersec = numSents / (((double)millis) / 1000);
NumberFormat nf = new DecimalFormat("0.00");
// easier way!
pwErr.Println("Parsed " + numWords + " words in " + numSents + " sentences (" + nf.Format(wordspersec) + " wds/sec; " + nf.Format(sentspersec) + " sents/sec).");
if (numFallback > 0)
{
pwErr.Println(" " + numFallback + " sentences were parsed by fallback to PCFG.");
}
if (numUnparsable > 0 || numNoMemory > 0 || numSkipped > 0)
{
pwErr.Println(" " + (numUnparsable + numNoMemory + numSkipped) + " sentences were not parsed:");
if (numUnparsable > 0)
{
pwErr.Println(" " + numUnparsable + " were not parsable with non-zero probability.");
}
if (numNoMemory > 0)
{
pwErr.Println(" " + numNoMemory + " were skipped because of insufficient memory.");
}
if (numSkipped > 0)
{
pwErr.Println(" " + numSkipped + " were skipped as length 0 or greater than " + op.testOptions.maxLength);
}
}
}
/// <summary>
/// An example of a command line is
/// <br />
/// java -mx1g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model /scr/horatio/dvparser/wsjPCFG.nocompact.simple.ser.gz -output cached9.simple.ser.gz -treebank /afs/ir/data/linguistic-data/Treebank/3/parsed/mrg/wsj 200-202
/// <br />
/// java -mx4g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model ~/scr/dvparser/wsjPCFG.nocompact.simple.ser.gz -output cached.train.simple.ser.gz -treebank /afs/ir/data/linguistic-data/Treebank/3/parsed/mrg/wsj 200-2199 -numThreads 6
/// <br />
/// java -mx4g edu.stanford.nlp.parser.dvparser.CacheParseHypotheses -model ~/scr/dvparser/chinese/xinhuaPCFG.ser.gz -output cached.xinhua.train.ser.gz -treebank /afs/ir/data/linguistic-data/Chinese-Treebank/6/data/utf8/bracketed 026-270,301-499,600-999
/// </summary>
/// <exception cref="System.IO.IOException"/>
public static void Main(string[] args)
{
string parserModel = null;
string output = null;
IList <Pair <string, IFileFilter> > treebanks = Generics.NewArrayList();
int dvKBest = 200;
int numThreads = 1;
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-dvKBest"))
{
dvKBest = System.Convert.ToInt32(args[argIndex + 1]);
argIndex += 2;
continue;
}
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-parser") || args[argIndex].Equals("-model"))
{
parserModel = args[argIndex + 1];
argIndex += 2;
continue;
}
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-output"))
{
output = args[argIndex + 1];
argIndex += 2;
continue;
}
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-treebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-treebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
treebanks.Add(treebankDescription);
continue;
}
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-numThreads"))
{
numThreads = System.Convert.ToInt32(args[argIndex + 1]);
argIndex += 2;
continue;
}
throw new ArgumentException("Unknown argument " + args[argIndex]);
}
if (parserModel == null)
{
throw new ArgumentException("Need to supply a parser model with -model");
}
if (output == null)
{
throw new ArgumentException("Need to supply an output filename with -output");
}
if (treebanks.IsEmpty())
{
throw new ArgumentException("Need to supply a treebank with -treebank");
}
log.Info("Writing output to " + output);
log.Info("Loading parser model " + parserModel);
log.Info("Writing " + dvKBest + " hypothesis trees for each tree");
LexicalizedParser parser = ((LexicalizedParser)LexicalizedParser.LoadModel(parserModel, "-dvKBest", int.ToString(dvKBest)));
CacheParseHypotheses cacher = new CacheParseHypotheses(parser);
ITreeTransformer transformer = DVParser.BuildTrainTransformer(parser.GetOp());
IList <Tree> sentences = new List <Tree>();
foreach (Pair <string, IFileFilter> description in treebanks)
{
log.Info("Reading trees from " + description.first);
Treebank treebank = parser.GetOp().tlpParams.MemoryTreebank();
treebank.LoadPath(description.first, description.second);
treebank = treebank.Transform(transformer);
Sharpen.Collections.AddAll(sentences, treebank);
}
log.Info("Processing " + sentences.Count + " trees");
IList <Pair <Tree, byte[]> > cache = Generics.NewArrayList();
transformer = new SynchronizedTreeTransformer(transformer);
MulticoreWrapper <Tree, Pair <Tree, byte[]> > wrapper = new MulticoreWrapper <Tree, Pair <Tree, byte[]> >(numThreads, new CacheParseHypotheses.CacheProcessor(cacher, parser, dvKBest, transformer));
foreach (Tree tree in sentences)
{
wrapper.Put(tree);
while (wrapper.Peek())
{
cache.Add(wrapper.Poll());
if (cache.Count % 10 == 0)
{
System.Console.Out.WriteLine("Processed " + cache.Count + " trees");
}
}
}
wrapper.Join();
while (wrapper.Peek())
{
cache.Add(wrapper.Poll());
if (cache.Count % 10 == 0)
{
System.Console.Out.WriteLine("Processed " + cache.Count + " trees");
}
}
System.Console.Out.WriteLine("Finished processing " + cache.Count + " trees");
IOUtils.WriteObjectToFile(cache, output);
}
/// <exception cref="System.Exception"/>
public static void RunCoref(Properties props)
{
/*
* property, environment setting
*/
Redwood.HideChannelsEverywhere("debug-cluster", "debug-mention", "debug-preprocessor", "debug-docreader", "debug-mergethres", "debug-featureselection", "debug-md");
int nThreads = HybridCorefProperties.GetThreadCounts(props);
string timeStamp = Calendar.GetInstance().GetTime().ToString().ReplaceAll("\\s", "-").ReplaceAll(":", "-");
Logger logger = Logger.GetLogger(typeof(Edu.Stanford.Nlp.Coref.Hybrid.HybridCorefSystem).FullName);
// set log file path
if (props.Contains(HybridCorefProperties.LogProp))
{
File logFile = new File(props.GetProperty(HybridCorefProperties.LogProp));
RedwoodConfiguration.Current().Handlers(RedwoodConfiguration.Handlers.File(logFile)).Apply();
Redwood.Log("Starting coref log");
}
log.Info(props.ToString());
if (HybridCorefProperties.CheckMemory(props))
{
CheckMemoryUsage();
}
Edu.Stanford.Nlp.Coref.Hybrid.HybridCorefSystem cs = new Edu.Stanford.Nlp.Coref.Hybrid.HybridCorefSystem(props);
/*
* output setting
*/
// prepare conll output
string goldOutput = null;
string beforeCorefOutput = null;
string afterCorefOutput = null;
PrintWriter writerGold = null;
PrintWriter writerBeforeCoref = null;
PrintWriter writerAfterCoref = null;
if (HybridCorefProperties.DoScore(props))
{
string pathOutput = CorefProperties.ConllOutputPath(props);
(new File(pathOutput)).Mkdir();
goldOutput = pathOutput + "output-" + timeStamp + ".gold.txt";
beforeCorefOutput = pathOutput + "output-" + timeStamp + ".predicted.txt";
afterCorefOutput = pathOutput + "output-" + timeStamp + ".coref.predicted.txt";
writerGold = new PrintWriter(new FileOutputStream(goldOutput));
writerBeforeCoref = new PrintWriter(new FileOutputStream(beforeCorefOutput));
writerAfterCoref = new PrintWriter(new FileOutputStream(afterCorefOutput));
}
// run coref
MulticoreWrapper <Pair <Document, Edu.Stanford.Nlp.Coref.Hybrid.HybridCorefSystem>, StringBuilder[]> wrapper = new MulticoreWrapper <Pair <Document, Edu.Stanford.Nlp.Coref.Hybrid.HybridCorefSystem>, StringBuilder[]>(nThreads, new _IThreadsafeProcessor_134
());
// conll output and logs
DateTime startTime = null;
if (HybridCorefProperties.CheckTime(props))
{
startTime = new DateTime();
System.Console.Error.Printf("END-TO-END COREF Start time: %s\n", startTime);
}
// run processes
int docCnt = 0;
while (true)
{
Document document = cs.docMaker.NextDoc();
if (document == null)
{
break;
}
wrapper.Put(Pair.MakePair(document, cs));
docCnt = LogOutput(wrapper, writerGold, writerBeforeCoref, writerAfterCoref, docCnt);
}
// Finished reading the input. Wait for jobs to finish
wrapper.Join();
docCnt = LogOutput(wrapper, writerGold, writerBeforeCoref, writerAfterCoref, docCnt);
IOUtils.CloseIgnoringExceptions(writerGold);
IOUtils.CloseIgnoringExceptions(writerBeforeCoref);
IOUtils.CloseIgnoringExceptions(writerAfterCoref);
if (HybridCorefProperties.CheckTime(props))
{
System.Console.Error.Printf("END-TO-END COREF Elapsed time: %.3f seconds\n", (((new DateTime()).GetTime() - startTime.GetTime()) / 1000F));
}
// System.err.printf("CORENLP PROCESS TIME TOTAL: %.3f seconds\n", cs.mentionExtractor.corenlpProcessTime);
if (HybridCorefProperties.CheckMemory(props))
{
CheckMemoryUsage();
}
// scoring
if (HybridCorefProperties.DoScore(props))
{
string summary = CorefScorer.GetEvalSummary(CorefProperties.GetScorerPath(props), goldOutput, beforeCorefOutput);
CorefScorer.PrintScoreSummary(summary, logger, false);
summary = CorefScorer.GetEvalSummary(CorefProperties.GetScorerPath(props), goldOutput, afterCorefOutput);
CorefScorer.PrintScoreSummary(summary, logger, true);
CorefScorer.PrintFinalConllScore(summary);
}
}