/// <summary>
/// Expected arguments are
/// <c>-gold gold -predicted predicted</c>
/// For example <br />
/// <c>java edu.stanford.nlp.sentiment.ExternalEvaluate annotatedTrees.txt predictedTrees.txt</c>
/// </summary>
public static void Main(string[] args)
{
RNNOptions curOptions = new RNNOptions();
string goldPath = null;
string predictedPath = null;
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-gold"))
{
goldPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-predicted"))
{
predictedPath = args[argIndex + 1];
argIndex += 2;
}
else
{
int newArgIndex = curOptions.SetOption(args, argIndex);
if (newArgIndex == argIndex)
{
throw new ArgumentException("Unknown argument " + args[argIndex]);
}
argIndex = newArgIndex;
}
}
}
if (goldPath == null)
{
log.Info("goldPath not set. Exit.");
System.Environment.Exit(-1);
}
if (predictedPath == null)
{
log.Info("predictedPath not set. Exit.");
System.Environment.Exit(-1);
}
// filterUnknown not supported because I'd need to know which sentences
// are removed to remove them from predicted
IList <Tree> goldTrees = SentimentUtils.ReadTreesWithGoldLabels(goldPath);
IList <Tree> predictedTrees = SentimentUtils.ReadTreesWithPredictedLabels(predictedPath);
Edu.Stanford.Nlp.Sentiment.ExternalEvaluate evaluator = new Edu.Stanford.Nlp.Sentiment.ExternalEvaluate(curOptions, predictedTrees);
evaluator.Eval(goldTrees);
evaluator.PrintSummary();
}
/// <summary>Trains a sentiment model.</summary>
/// <remarks>
/// Trains a sentiment model.
/// The -trainPath argument points to a labeled sentiment treebank.
/// The trees in this data will be used to train the model parameters (also to seed the model vocabulary).
/// The -devPath argument points to a second labeled sentiment treebank.
/// The trees in this data will be used to periodically evaluate the performance of the model.
/// We won't train on this data; it will only be used to test how well the model generalizes to unseen data.
/// The -model argument specifies where to save the learned sentiment model.
/// </remarks>
/// <param name="args">Command line arguments</param>
public static void Main(string[] args)
{
RNNOptions op = new RNNOptions();
string trainPath = "sentimentTreesDebug.txt";
string devPath = null;
bool runGradientCheck = false;
bool runTraining = false;
bool filterUnknown = false;
string modelPath = null;
for (int argIndex = 0; argIndex < args.Length;)
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-train"))
{
runTraining = true;
argIndex++;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-gradientcheck"))
{
runGradientCheck = true;
argIndex++;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-trainpath"))
{
trainPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-devpath"))
{
devPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-model"))
{
modelPath = args[argIndex + 1];
argIndex += 2;
}
else
{
if (Sharpen.Runtime.EqualsIgnoreCase(args[argIndex], "-filterUnknown"))
{
filterUnknown = true;
argIndex++;
}
else
{
int newArgIndex = op.SetOption(args, argIndex);
if (newArgIndex == argIndex)
{
throw new ArgumentException("Unknown argument " + args[argIndex]);
}
argIndex = newArgIndex;
}
}
}
}
}
}
}
// read in the trees
IList <Tree> trainingTrees = SentimentUtils.ReadTreesWithGoldLabels(trainPath);
log.Info("Read in " + trainingTrees.Count + " training trees");
if (filterUnknown)
{
trainingTrees = SentimentUtils.FilterUnknownRoots(trainingTrees);
log.Info("Filtered training trees: " + trainingTrees.Count);
}
IList <Tree> devTrees = null;
if (devPath != null)
{
devTrees = SentimentUtils.ReadTreesWithGoldLabels(devPath);
log.Info("Read in " + devTrees.Count + " dev trees");
if (filterUnknown)
{
devTrees = SentimentUtils.FilterUnknownRoots(devTrees);
log.Info("Filtered dev trees: " + devTrees.Count);
}
}
// TODO: binarize the trees, then collapse the unary chains.
// Collapsed unary chains always have the label of the top node in
// the chain
// Note: the sentiment training data already has this done.
// However, when we handle trees given to us from the Stanford Parser,
// we will have to perform this step
// build an uninitialized SentimentModel from the binary productions
log.Info("Sentiment model options:\n" + op);
SentimentModel model = new SentimentModel(op, trainingTrees);
if (op.trainOptions.initialMatrixLogPath != null)
{
StringUtils.PrintToFile(new File(op.trainOptions.initialMatrixLogPath), model.ToString(), false, false, "utf-8");
}
// TODO: need to handle unk rules somehow... at test time the tree
// structures might have something that we never saw at training
// time. for example, we could put a threshold on all of the
// rules at training time and anything that doesn't meet that
// threshold goes into the unk. perhaps we could also use some
// component of the accepted training rules to build up the "unk"
// parameter in case there are no rules that don't meet the
// threshold
if (runGradientCheck)
{
RunGradientCheck(model, trainingTrees);
}
if (runTraining)
{
Train(model, modelPath, trainingTrees, devTrees);
model.SaveSerialized(modelPath);
}
}