/// <summary>
/// An example command line for training a new parser:
/// <br />
/// nohup java -mx6g edu.stanford.nlp.parser.dvparser.DVParser -cachedTrees /scr/nlp/data/dvparser/wsj/cached.wsj.train.simple.ser.gz -train -testTreebank /afs/ir/data/linguistic-data/Treebank/3/parsed/mrg/wsj/22 2200-2219 -debugOutputFrequency 400 -nofilter -trainingThreads 5 -parser /u/nlp/data/lexparser/wsjPCFG.nocompact.simple.ser.gz -trainingIterations 40 -batchSize 25 -model /scr/nlp/data/dvparser/wsj/wsj.combine.v2.ser.gz -unkWord "*UNK*" -dvCombineCategories > /scr/nlp/data/dvparser/wsj/wsj.combine.v2.out 2>&1 &
/// </summary>
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
public static void Main(string[] args)
{
if (args.Length == 0)
{
Help();
System.Environment.Exit(2);
}
log.Info("Running DVParser with arguments:");
foreach (string arg in args)
{
log.Info(" " + arg);
}
log.Info();
string parserPath = null;
string trainTreebankPath = null;
IFileFilter trainTreebankFilter = null;
string cachedTrainTreesPath = null;
bool runGradientCheck = false;
bool runTraining = false;
string testTreebankPath = null;
IFileFilter testTreebankFilter = null;
string initialModelPath = null;
string modelPath = null;
bool filter = true;
string resultsRecordPath = null;
IList <string> unusedArgs = new List <string>();
// These parameters can be null or 0 if the model was not
// serialized with the new parameters. Setting the options at the
// command line will override these defaults.
// TODO: if/when we integrate back into the main branch and
// rebuild models, we can get rid of this
IList <string> argsWithDefaults = new List <string>(Arrays.AsList(new string[] { "-wordVectorFile", Options.LexOptions.DefaultWordVectorFile, "-dvKBest", int.ToString(TrainOptions.DefaultKBest), "-batchSize", int.ToString(TrainOptions.DefaultBatchSize
), "-trainingIterations", int.ToString(TrainOptions.DefaultTrainingIterations), "-qnIterationsPerBatch", int.ToString(TrainOptions.DefaultQnIterationsPerBatch), "-regCost", double.ToString(TrainOptions.DefaultRegcost), "-learningRate", double
.ToString(TrainOptions.DefaultLearningRate), "-deltaMargin", double.ToString(TrainOptions.DefaultDeltaMargin), "-unknownNumberVector", "-unknownDashedWordVectors", "-unknownCapsVector", "-unknownchinesepercentvector", "-unknownchinesenumbervector"
, "-unknownchineseyearvector", "-unkWord", "*UNK*", "-transformMatrixType", "DIAGONAL", "-scalingForInit", double.ToString(TrainOptions.DefaultScalingForInit), "-trainWordVectors" }));
Sharpen.Collections.AddAll(argsWithDefaults, Arrays.AsList(args));
args = Sharpen.Collections.ToArray(argsWithDefaults, new string[argsWithDefaults.Count]);
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-parser"))
{
parserPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
testTreebankPath = treebankDescription.First();
testTreebankFilter = treebankDescription.Second();
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-treebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-treebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
trainTreebankPath = treebankDescription.First();
trainTreebankFilter = treebankDescription.Second();
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-cachedTrees"))
{
cachedTrainTreesPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-runGradientCheck"))
{
runGradientCheck = true;
argIndex++;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-train"))
{
runTraining = true;
argIndex++;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
modelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-nofilter"))
{
filter = false;
argIndex++;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-continueTraining"))
{
runTraining = true;
filter = false;
initialModelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-resultsRecord"))
{
resultsRecordPath = args[argIndex + 1];
argIndex += 2;
}
else
{
unusedArgs.Add(args[argIndex++]);
}
}
}
}
}
}
}
}
}
}
}
if (parserPath == null && modelPath == null)
{
throw new ArgumentException("Must supply either a base parser model with -parser or a serialized DVParser with -model");
}
if (!runTraining && modelPath == null && !runGradientCheck)
{
throw new ArgumentException("Need to either train a new model, run the gradient check or specify a model to load with -model");
}
string[] newArgs = Sharpen.Collections.ToArray(unusedArgs, new string[unusedArgs.Count]);
Edu.Stanford.Nlp.Parser.Dvparser.DVParser dvparser = null;
LexicalizedParser lexparser = null;
if (initialModelPath != null)
{
lexparser = ((LexicalizedParser)LexicalizedParser.LoadModel(initialModelPath, newArgs));
DVModel model = GetModelFromLexicalizedParser(lexparser);
dvparser = new Edu.Stanford.Nlp.Parser.Dvparser.DVParser(model, lexparser);
}
else
{
if (runTraining || runGradientCheck)
{
lexparser = ((LexicalizedParser)LexicalizedParser.LoadModel(parserPath, newArgs));
dvparser = new Edu.Stanford.Nlp.Parser.Dvparser.DVParser(lexparser);
}
else
{
if (modelPath != null)
{
lexparser = ((LexicalizedParser)LexicalizedParser.LoadModel(modelPath, newArgs));
DVModel model = GetModelFromLexicalizedParser(lexparser);
dvparser = new Edu.Stanford.Nlp.Parser.Dvparser.DVParser(model, lexparser);
}
}
}
IList <Tree> trainSentences = new List <Tree>();
IdentityHashMap <Tree, byte[]> trainCompressedParses = Generics.NewIdentityHashMap();
if (cachedTrainTreesPath != null)
{
foreach (string path in cachedTrainTreesPath.Split(","))
{
IList <Pair <Tree, byte[]> > cache = IOUtils.ReadObjectFromFile(path);
foreach (Pair <Tree, byte[]> pair in cache)
{
trainSentences.Add(pair.First());
trainCompressedParses[pair.First()] = pair.Second();
}
log.Info("Read in " + cache.Count + " trees from " + path);
}
}
if (trainTreebankPath != null)
{
// TODO: make the transformer a member of the model?
ITreeTransformer transformer = BuildTrainTransformer(dvparser.GetOp());
Treebank treebank = dvparser.GetOp().tlpParams.MemoryTreebank();
treebank.LoadPath(trainTreebankPath, trainTreebankFilter);
treebank = treebank.Transform(transformer);
log.Info("Read in " + treebank.Count + " trees from " + trainTreebankPath);
CacheParseHypotheses cacher = new CacheParseHypotheses(dvparser.parser);
CacheParseHypotheses.CacheProcessor processor = new CacheParseHypotheses.CacheProcessor(cacher, lexparser, dvparser.op.trainOptions.dvKBest, transformer);
foreach (Tree tree in treebank)
{
trainSentences.Add(tree);
trainCompressedParses[tree] = processor.Process(tree).second;
}
//System.out.println(tree);
log.Info("Finished parsing " + treebank.Count + " trees, getting " + dvparser.op.trainOptions.dvKBest + " hypotheses each");
}
if ((runTraining || runGradientCheck) && filter)
{
log.Info("Filtering rules for the given training set");
dvparser.dvModel.SetRulesForTrainingSet(trainSentences, trainCompressedParses);
log.Info("Done filtering rules; " + dvparser.dvModel.numBinaryMatrices + " binary matrices, " + dvparser.dvModel.numUnaryMatrices + " unary matrices, " + dvparser.dvModel.wordVectors.Count + " word vectors");
}
//dvparser.dvModel.printAllMatrices();
Treebank testTreebank = null;
if (testTreebankPath != null)
{
log.Info("Reading in trees from " + testTreebankPath);
if (testTreebankFilter != null)
{
log.Info("Filtering on " + testTreebankFilter);
}
testTreebank = dvparser.GetOp().tlpParams.MemoryTreebank();
testTreebank.LoadPath(testTreebankPath, testTreebankFilter);
log.Info("Read in " + testTreebank.Count + " trees for testing");
}
// runGradientCheck= true;
if (runGradientCheck)
{
log.Info("Running gradient check on " + trainSentences.Count + " trees");
dvparser.RunGradientCheck(trainSentences, trainCompressedParses);
}
if (runTraining)
{
log.Info("Training the RNN parser");
log.Info("Current train options: " + dvparser.GetOp().trainOptions);
dvparser.Train(trainSentences, trainCompressedParses, testTreebank, modelPath, resultsRecordPath);
if (modelPath != null)
{
dvparser.SaveModel(modelPath);
}
}
if (testTreebankPath != null)
{
EvaluateTreebank evaluator = new EvaluateTreebank(dvparser.AttachModelToLexicalizedParser());
evaluator.TestOnTreebank(testTreebank);
}
log.Info("Successfully ran DVParser");
}
/// <exception cref="System.IO.IOException"/>
public static void Main(string[] args)
{
string modelPath = null;
string outputPath = null;
string inputPath = null;
string testTreebankPath = null;
IFileFilter testTreebankFilter = null;
IList <string> unusedArgs = Generics.NewArrayList();
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
modelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-output"))
{
outputPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-input"))
{
inputPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
testTreebankPath = treebankDescription.First();
testTreebankFilter = treebankDescription.Second();
}
else
{
unusedArgs.Add(args[argIndex++]);
}
}
}
}
}
string[] newArgs = Sharpen.Collections.ToArray(unusedArgs, new string[unusedArgs.Count]);
LexicalizedParser parser = ((LexicalizedParser)LexicalizedParser.LoadModel(modelPath, newArgs));
DVModel model = DVParser.GetModelFromLexicalizedParser(parser);
File outputFile = new File(outputPath);
FileSystem.CheckNotExistsOrFail(outputFile);
FileSystem.MkdirOrFail(outputFile);
int count = 0;
if (inputPath != null)
{
Reader input = new BufferedReader(new FileReader(inputPath));
DocumentPreprocessor processor = new DocumentPreprocessor(input);
foreach (IList <IHasWord> sentence in processor)
{
count++;
// index from 1
IParserQuery pq = parser.ParserQuery();
if (!(pq is RerankingParserQuery))
{
throw new ArgumentException("Expected a RerankingParserQuery");
}
RerankingParserQuery rpq = (RerankingParserQuery)pq;
if (!rpq.Parse(sentence))
{
throw new Exception("Unparsable sentence: " + sentence);
}
IRerankerQuery reranker = rpq.RerankerQuery();
if (!(reranker is DVModelReranker.Query))
{
throw new ArgumentException("Expected a DVModelReranker");
}
DeepTree deepTree = ((DVModelReranker.Query)reranker).GetDeepTrees()[0];
IdentityHashMap <Tree, SimpleMatrix> vectors = deepTree.GetVectors();
foreach (KeyValuePair <Tree, SimpleMatrix> entry in vectors)
{
log.Info(entry.Key + " " + entry.Value);
}
FileWriter fout = new FileWriter(outputPath + File.separator + "sentence" + count + ".txt");
BufferedWriter bout = new BufferedWriter(fout);
bout.Write(SentenceUtils.ListToString(sentence));
bout.NewLine();
bout.Write(deepTree.GetTree().ToString());
bout.NewLine();
foreach (IHasWord word in sentence)
{
OutputMatrix(bout, model.GetWordVector(word.Word()));
}
Tree rootTree = FindRootTree(vectors);
OutputTreeMatrices(bout, rootTree, vectors);
bout.Flush();
fout.Close();
}
}
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
public static void Main(string[] args)
{
string dvmodelFile = null;
string lexparserFile = null;
string testTreebankPath = null;
IFileFilter testTreebankFilter = null;
IList <string> unusedArgs = new List <string>();
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-lexparser"))
{
lexparserFile = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
testTreebankPath = treebankDescription.First();
testTreebankFilter = treebankDescription.Second();
}
else
{
unusedArgs.Add(args[argIndex++]);
}
}
}
log.Info("Loading lexparser from: " + lexparserFile);
string[] newArgs = Sharpen.Collections.ToArray(unusedArgs, new string[unusedArgs.Count]);
LexicalizedParser lexparser = ((LexicalizedParser)LexicalizedParser.LoadModel(lexparserFile, newArgs));
log.Info("... done");
Treebank testTreebank = null;
if (testTreebankPath != null)
{
log.Info("Reading in trees from " + testTreebankPath);
if (testTreebankFilter != null)
{
log.Info("Filtering on " + testTreebankFilter);
}
testTreebank = lexparser.GetOp().tlpParams.MemoryTreebank();
testTreebank.LoadPath(testTreebankPath, testTreebankFilter);
log.Info("Read in " + testTreebank.Count + " trees for testing");
}
double[] labelResults = new double[weights.Length];
double[] tagResults = new double[weights.Length];
for (int i = 0; i < weights.Length; ++i)
{
lexparser.GetOp().baseParserWeight = weights[i];
EvaluateTreebank evaluator = new EvaluateTreebank(lexparser);
evaluator.TestOnTreebank(testTreebank);
labelResults[i] = evaluator.GetLBScore();
tagResults[i] = evaluator.GetTagScore();
}
for (int i_1 = 0; i_1 < weights.Length; ++i_1)
{
log.Info("LexicalizedParser weight " + weights[i_1] + ": labeled " + labelResults[i_1] + " tag " + tagResults[i_1]);
}
}
public static void Main(string[] args)
{
IList <string> remainingArgs = Generics.NewArrayList();
IList <Pair <string, IFileFilter> > trainTreebankPath = null;
Pair <string, IFileFilter> testTreebankPath = null;
Pair <string, IFileFilter> devTreebankPath = null;
string serializedPath = null;
string tlppClass = null;
string continueTraining = null;
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-trainTreebank"))
{
if (trainTreebankPath == null)
{
trainTreebankPath = Generics.NewArrayList();
}
trainTreebankPath.Add(ArgUtils.GetTreebankDescription(args, argIndex, "-trainTreebank"));
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
testTreebankPath = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-devTreebank"))
{
devTreebankPath = ArgUtils.GetTreebankDescription(args, argIndex, "-devTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-serializedPath") || Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
serializedPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-tlpp"))
{
tlppClass = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-continueTraining"))
{
continueTraining = args[argIndex + 1];
argIndex += 2;
}
else
{
remainingArgs.Add(args[argIndex]);
++argIndex;
}
}
}
}
}
}
}
string[] newArgs = new string[remainingArgs.Count];
newArgs = Sharpen.Collections.ToArray(remainingArgs, newArgs);
if (trainTreebankPath == null && serializedPath == null)
{
throw new ArgumentException("Must specify a treebank to train from with -trainTreebank or a parser to load with -serializedPath");
}
ShiftReduceParser parser = null;
if (trainTreebankPath != null)
{
log.Info("Training ShiftReduceParser");
log.Info("Initial arguments:");
log.Info(" " + StringUtils.Join(args));
if (continueTraining != null)
{
parser = ((ShiftReduceParser)ShiftReduceParser.LoadModel(continueTraining, ArrayUtils.Concatenate(ForceTags, newArgs)));
}
else
{
ShiftReduceOptions op = BuildTrainingOptions(tlppClass, newArgs);
parser = new ShiftReduceParser(op);
}
parser.Train(trainTreebankPath, devTreebankPath, serializedPath);
parser.SaveModel(serializedPath);
}
if (serializedPath != null && parser == null)
{
parser = ((ShiftReduceParser)ShiftReduceParser.LoadModel(serializedPath, ArrayUtils.Concatenate(ForceTags, newArgs)));
}
//parser.outputStats();
if (testTreebankPath != null)
{
log.Info("Loading test trees from " + testTreebankPath.First());
Treebank testTreebank = parser.op.tlpParams.MemoryTreebank();
testTreebank.LoadPath(testTreebankPath.First(), testTreebankPath.Second());
log.Info("Loaded " + testTreebank.Count + " trees");
EvaluateTreebank evaluator = new EvaluateTreebank(parser.op, null, parser);
evaluator.TestOnTreebank(testTreebank);
}
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.TypeLoadException"/>
public static void Main(string[] args)
{
string modelPath = null;
IList <string> baseModelPaths = null;
string testTreebankPath = null;
IFileFilter testTreebankFilter = null;
IList <string> unusedArgs = new List <string>();
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
modelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
testTreebankPath = treebankDescription.First();
testTreebankFilter = treebankDescription.Second();
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-baseModels"))
{
argIndex++;
baseModelPaths = new List <string>();
while (argIndex < args.Length && args[argIndex][0] != '-')
{
baseModelPaths.Add(args[argIndex++]);
}
if (baseModelPaths.Count == 0)
{
throw new ArgumentException("Found an argument -baseModels with no actual models named");
}
}
else
{
unusedArgs.Add(args[argIndex++]);
}
}
}
}
string[] newArgs = Sharpen.Collections.ToArray(unusedArgs, new string[unusedArgs.Count]);
LexicalizedParser underlyingParser = null;
Options options = null;
LexicalizedParser combinedParser = null;
if (baseModelPaths != null)
{
IList <DVModel> dvparsers = new List <DVModel>();
foreach (string baseModelPath in baseModelPaths)
{
log.Info("Loading serialized DVParser from " + baseModelPath);
LexicalizedParser dvparser = ((LexicalizedParser)LexicalizedParser.LoadModel(baseModelPath));
IReranker reranker = dvparser.reranker;
if (!(reranker is DVModelReranker))
{
throw new ArgumentException("Expected parsers with DVModel embedded");
}
dvparsers.Add(((DVModelReranker)reranker).GetModel());
if (underlyingParser == null)
{
underlyingParser = dvparser;
options = underlyingParser.GetOp();
// TODO: other parser's options?
options.SetOptions(newArgs);
}
log.Info("... done");
}
combinedParser = LexicalizedParser.CopyLexicalizedParser(underlyingParser);
CombinedDVModelReranker reranker_1 = new CombinedDVModelReranker(options, dvparsers);
combinedParser.reranker = reranker_1;
combinedParser.SaveParserToSerialized(modelPath);
}
else
{
throw new ArgumentException("Need to specify -model to load an already prepared CombinedParser");
}
Treebank testTreebank = null;
if (testTreebankPath != null)
{
log.Info("Reading in trees from " + testTreebankPath);
if (testTreebankFilter != null)
{
log.Info("Filtering on " + testTreebankFilter);
}
testTreebank = combinedParser.GetOp().tlpParams.MemoryTreebank();
testTreebank.LoadPath(testTreebankPath, testTreebankFilter);
log.Info("Read in " + testTreebank.Count + " trees for testing");
EvaluateTreebank evaluator = new EvaluateTreebank(combinedParser.GetOp(), null, combinedParser);
evaluator.TestOnTreebank(testTreebank);
}
}
/// <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 Main(string[] args)
{
string modelPath = null;
string outputPath = null;
string testTreebankPath = null;
IFileFilter testTreebankFilter = null;
IList <string> unusedArgs = new List <string>();
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
modelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-testTreebank"))
{
Pair <string, IFileFilter> treebankDescription = ArgUtils.GetTreebankDescription(args, argIndex, "-testTreebank");
argIndex = argIndex + ArgUtils.NumSubArgs(args, argIndex) + 1;
testTreebankPath = treebankDescription.First();
testTreebankFilter = treebankDescription.Second();
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-output"))
{
outputPath = args[argIndex + 1];
argIndex += 2;
}
else
{
unusedArgs.Add(args[argIndex++]);
}
}
}
}
if (modelPath == null)
{
throw new ArgumentException("Need to specify -model");
}
if (testTreebankPath == null)
{
throw new ArgumentException("Need to specify -testTreebank");
}
if (outputPath == null)
{
throw new ArgumentException("Need to specify -output");
}
string[] newArgs = Sharpen.Collections.ToArray(unusedArgs, new string[unusedArgs.Count]);
LexicalizedParser lexparser = ((LexicalizedParser)LexicalizedParser.LoadModel(modelPath, newArgs));
Treebank testTreebank = null;
if (testTreebankPath != null)
{
log.Info("Reading in trees from " + testTreebankPath);
if (testTreebankFilter != null)
{
log.Info("Filtering on " + testTreebankFilter);
}
testTreebank = lexparser.GetOp().tlpParams.MemoryTreebank();
testTreebank.LoadPath(testTreebankPath, testTreebankFilter);
log.Info("Read in " + testTreebank.Count + " trees for testing");
}
FileWriter @out = new FileWriter(outputPath);
BufferedWriter bout = new BufferedWriter(@out);
log.Info("Parsing " + testTreebank.Count + " trees");
int count = 0;
IList <FindNearestNeighbors.ParseRecord> records = Generics.NewArrayList();
foreach (Tree goldTree in testTreebank)
{
IList <Word> tokens = goldTree.YieldWords();
IParserQuery parserQuery = lexparser.ParserQuery();
if (!parserQuery.Parse(tokens))
{
throw new AssertionError("Could not parse: " + tokens);
}
if (!(parserQuery is RerankingParserQuery))
{
throw new ArgumentException("Expected a LexicalizedParser with a Reranker attached");
}
RerankingParserQuery rpq = (RerankingParserQuery)parserQuery;
if (!(rpq.RerankerQuery() is DVModelReranker.Query))
{
throw new ArgumentException("Expected a LexicalizedParser with a DVModel attached");
}
DeepTree tree = ((DVModelReranker.Query)rpq.RerankerQuery()).GetDeepTrees()[0];
SimpleMatrix rootVector = null;
foreach (KeyValuePair <Tree, SimpleMatrix> entry in tree.GetVectors())
{
if (entry.Key.Label().Value().Equals("ROOT"))
{
rootVector = entry.Value;
break;
}
}
if (rootVector == null)
{
throw new AssertionError("Could not find root nodevector");
}
@out.Write(tokens + "\n");
@out.Write(tree.GetTree() + "\n");
for (int i = 0; i < rootVector.GetNumElements(); ++i)
{
@out.Write(" " + rootVector.Get(i));
}
@out.Write("\n\n\n");
count++;
if (count % 10 == 0)
{
log.Info(" " + count);
}
records.Add(new FindNearestNeighbors.ParseRecord(tokens, goldTree, tree.GetTree(), rootVector, tree.GetVectors()));
}
log.Info(" done parsing");
IList <Pair <Tree, SimpleMatrix> > subtrees = Generics.NewArrayList();
foreach (FindNearestNeighbors.ParseRecord record in records)
{
foreach (KeyValuePair <Tree, SimpleMatrix> entry in record.nodeVectors)
{
if (entry.Key.GetLeaves().Count <= maxLength)
{
subtrees.Add(Pair.MakePair(entry.Key, entry.Value));
}
}
}
log.Info("There are " + subtrees.Count + " subtrees in the set of trees");
PriorityQueue <ScoredObject <Pair <Tree, Tree> > > bestmatches = new PriorityQueue <ScoredObject <Pair <Tree, Tree> > >(101, ScoredComparator.DescendingComparator);
for (int i_1 = 0; i_1 < subtrees.Count; ++i_1)
{
log.Info(subtrees[i_1].First().YieldWords());
log.Info(subtrees[i_1].First());
for (int j = 0; j < subtrees.Count; ++j)
{
if (i_1 == j)
{
continue;
}
// TODO: look at basic category?
double normF = subtrees[i_1].Second().Minus(subtrees[j].Second()).NormF();
bestmatches.Add(new ScoredObject <Pair <Tree, Tree> >(Pair.MakePair(subtrees[i_1].First(), subtrees[j].First()), normF));
if (bestmatches.Count > 100)
{
bestmatches.Poll();
}
}
IList <ScoredObject <Pair <Tree, Tree> > > ordered = Generics.NewArrayList();
while (bestmatches.Count > 0)
{
ordered.Add(bestmatches.Poll());
}
Java.Util.Collections.Reverse(ordered);
foreach (ScoredObject <Pair <Tree, Tree> > pair in ordered)
{
log.Info(" MATCHED " + pair.Object().second.YieldWords() + " ... " + pair.Object().Second() + " with a score of " + pair.Score());
}
log.Info();
log.Info();
bestmatches.Clear();
}
/*
* for (int i = 0; i < records.size(); ++i) {
* if (i % 10 == 0) {
* log.info(" " + i);
* }
* List<ScoredObject<ParseRecord>> scored = Generics.newArrayList();
* for (int j = 0; j < records.size(); ++j) {
* if (i == j) continue;
*
* double score = 0.0;
* int matches = 0;
* for (Map.Entry<Tree, SimpleMatrix> first : records.get(i).nodeVectors.entrySet()) {
* for (Map.Entry<Tree, SimpleMatrix> second : records.get(j).nodeVectors.entrySet()) {
* String firstBasic = dvparser.dvModel.basicCategory(first.getKey().label().value());
* String secondBasic = dvparser.dvModel.basicCategory(second.getKey().label().value());
* if (firstBasic.equals(secondBasic)) {
++matches;
* double normF = first.getValue().minus(second.getValue()).normF();
* score += normF * normF;
* }
* }
* }
* if (matches == 0) {
* score = Double.POSITIVE_INFINITY;
* } else {
* score = score / matches;
* }
* //double score = records.get(i).vector.minus(records.get(j).vector).normF();
* scored.add(new ScoredObject<ParseRecord>(records.get(j), score));
* }
* Collections.sort(scored, ScoredComparator.ASCENDING_COMPARATOR);
*
* out.write(records.get(i).sentence.toString() + "\n");
* for (int j = 0; j < numNeighbors; ++j) {
* out.write(" " + scored.get(j).score() + ": " + scored.get(j).object().sentence + "\n");
* }
* out.write("\n\n");
* }
* log.info();
*/
bout.Flush();
@out.Flush();
@out.Close();
}