protected virtual int[] TrainSequencePair(ISequence sequence, RunningMode runningMode, bool outputRawScore, out Matrix <float> m)
{
SequencePair pSequence = sequence as SequencePair;
var tgtSequence = pSequence.tgtSequence;
//Reset all layers
foreach (var layer in HiddenLayerList)
{
layer.Reset();
}
Sequence srcSequence;
//Extract features from source sentences
srcSequence = pSequence.autoEncoder.Config.BuildSequence(pSequence.srcSentence);
ExtractSourceSentenceFeature(pSequence.autoEncoder, srcSequence, tgtSequence.SparseFeatureSize);
var numStates = pSequence.tgtSequence.States.Length;
var numLayers = HiddenLayerList.Count;
var predicted = new int[numStates];
var previousLables = new int[numStates];
m = outputRawScore ? new Matrix <float>(numStates, OutputLayer.LayerSize) : null;
//Set target sentence labels into short list in output layer
OutputLayer.LabelShortList.Clear();
foreach (var state in tgtSequence.States)
{
OutputLayer.LabelShortList.Add(state.Label);
}
CreateDenseFeatureList();
for (int i = 0; i < numLayers; i++)
{
srcHiddenAvgOutput.CopyTo(denseFeaturesList[i], 0);
}
srcHiddenAvgOutput.CopyTo(denseFeaturesList[numLayers], 0);
var sparseVector = new SparseVector();
for (var curState = 0; curState < numStates; curState++)
{
//Build runtime features
var state = tgtSequence.States[curState];
SetRuntimeFeatures(state, curState, numStates, (runningMode == RunningMode.Training) ? previousLables : predicted);
//Build sparse features for all layers
sparseVector.Clean();
sparseVector.SetLength(tgtSequence.SparseFeatureSize + srcSequence.SparseFeatureSize);
sparseVector.AddKeyValuePairData(state.SparseFeature);
sparseVector.AddKeyValuePairData(srcSparseFeatures);
//Compute first layer
state.DenseFeature.CopyTo().CopyTo(denseFeaturesList[0], srcHiddenAvgOutput.Length);
HiddenLayerList[0].ForwardPass(sparseVector, denseFeaturesList[0]);
//Compute middle layers
for (var i = 1; i < numLayers; i++)
{
//We use previous layer's output as dense feature for current layer
HiddenLayerList[i - 1].Cells.CopyTo(denseFeaturesList[i], srcHiddenAvgOutput.Length);
HiddenLayerList[i].ForwardPass(sparseVector, denseFeaturesList[i]);
}
//Compute output layer
HiddenLayerList[numLayers - 1].Cells.CopyTo(denseFeaturesList[numLayers], srcHiddenAvgOutput.Length);
OutputLayer.ForwardPass(sparseVector, denseFeaturesList[numLayers]);
if (m != null)
{
OutputLayer.Cells.CopyTo(m[curState], 0);
}
predicted[curState] = OutputLayer.GetBestOutputIndex();
if (runningMode == RunningMode.Training)
{
previousLables[curState] = state.Label;
// error propogation
OutputLayer.ComputeLayerErr(CRFSeqOutput, state, curState);
//propogate errors to each layer from output layer to input layer
HiddenLayerList[numLayers - 1].ComputeLayerErr(OutputLayer);
for (var i = numLayers - 2; i >= 0; i--)
{
HiddenLayerList[i].ComputeLayerErr(HiddenLayerList[i + 1]);
}
//Update net weights
OutputLayer.BackwardPass();
for (var i = 0; i < numLayers; i++)
{
HiddenLayerList[i].BackwardPass();
}
}
}
return(predicted);
}
protected int[] PredictTargetSentence(Sentence sentence, Config featurizer, out Matrix <float> m)
{
m = null;
var curState = featurizer.BuildState(new[] { "<s>" });
curState.Label = featurizer.TagSet.GetIndex("<s>");
//Reset all layers
foreach (var layer in HiddenLayerList)
{
layer.Reset();
}
//Extract features from source sentence
var srcSequence = featurizer.Seq2SeqAutoEncoder.Config.BuildSequence(sentence);
ExtractSourceSentenceFeature(featurizer.Seq2SeqAutoEncoder, srcSequence, curState.SparseFeature.Length);
var numLayers = HiddenLayerList.Count;
var predicted = new List <int> {
curState.Label
};
CreateDenseFeatureList();
for (int i = 0; i < numLayers; i++)
{
srcHiddenAvgOutput.CopyTo(denseFeaturesList[i], 0);
}
srcHiddenAvgOutput.CopyTo(denseFeaturesList[numLayers], 0);
var sparseVector = new SparseVector();
while (true)
{
//Build sparse features
sparseVector.Clean();
sparseVector.SetLength(curState.SparseFeature.Length + srcSequence.SparseFeatureSize);
sparseVector.AddKeyValuePairData(curState.SparseFeature);
sparseVector.AddKeyValuePairData(srcSparseFeatures);
//Compute first layer
curState.DenseFeature.CopyTo().CopyTo(denseFeaturesList[0], srcHiddenAvgOutput.Length);
HiddenLayerList[0].ForwardPass(sparseVector, denseFeaturesList[0]);
//Compute middle layers
for (var i = 1; i < numLayers; i++)
{
//We use previous layer's output as dense feature for current layer
HiddenLayerList[i - 1].Cells.CopyTo(denseFeaturesList[i], srcHiddenAvgOutput.Length);
HiddenLayerList[i].ForwardPass(sparseVector, denseFeaturesList[i]);
}
//Compute output layer
HiddenLayerList[numLayers - 1].Cells.CopyTo(denseFeaturesList[numLayers], srcHiddenAvgOutput.Length);
OutputLayer.ForwardPass(sparseVector, denseFeaturesList[numLayers]);
var nextTagId = OutputLayer.GetBestOutputIndex();
var nextWord = featurizer.TagSet.GetTagName(nextTagId);
curState = featurizer.BuildState(new[] { nextWord });
curState.Label = nextTagId;
predicted.Add(nextTagId);
if (nextWord == "</s>" || predicted.Count >= 100)
{
break;
}
}
return(predicted.ToArray());
}
