//return the gradient of -log{P(y*|x,w)} as follows: E_{P(y|x)}(F(x,y)) - F(x,y*)
virtual public double getGrad(List <double> vecGrad, model m, dataSeq x, baseHashSet <int> idSet)
{
if (idSet != null)
{
idSet.Clear();
}
int nTag = m.NTag;
//compute beliefs
belief bel = new belief(x.Count, nTag);
belief belMasked = new belief(x.Count, nTag);
_inf.getBeliefs(bel, m, x, false);
_inf.getBeliefs(belMasked, m, x, true);
double ZGold = belMasked.Z;
double Z = bel.Z;
List <featureTemp> fList;
for (int i = 0; i < x.Count; i++)
{
fList = _fGene.getFeatureTemp(x, i);
for (int j = 0; j < fList.Count; j++)
{
featureTemp im = fList[j];
int id = im.id;
double v = im.val;
for (int s = 0; s < nTag; s++)
{
int f = _fGene.getNodeFeatID(id, s);
if (idSet != null)
{
idSet.Add(f);
}
vecGrad[f] += bel.belState[i][s] * v;
vecGrad[f] -= belMasked.belState[i][s] * v;
}
}
}
for (int i = 1; i < x.Count; i++)
{
for (int s = 0; s < nTag; s++)
{
for (int sPre = 0; sPre < nTag; sPre++)
{
int f = _fGene.getEdgeFeatID(sPre, s);
if (idSet != null)
{
idSet.Add(f);
}
vecGrad[f] += bel.belEdge[i][sPre, s];
vecGrad[f] -= belMasked.belEdge[i][sPre, s];
}
}
}
return(Z - ZGold);
}
virtual public void getLogYY(model m, dataSeq x, int i, ref dMatrix YY, ref List <double> Y, bool takeExp, bool mask)
{
YY.set(0);
listTool.listSet(ref Y, 0);
List <double> w = m.W;
List <featureTemp> fList = _fGene.getFeatureTemp(x, i);
int nTag = m.NTag;
for (int j = 0; j < fList.Count; j++)
{
featureTemp ptr = fList[j];
int id = ptr.id;
double v = ptr.val;
for (int s = 0; s < nTag; s++)
{
int f = _fGene.getNodeFeatID(id, s);
Y[s] += w[f] * v;
}
}
if (i > 0)
{
for (int s = 0; s < nTag; s++)
{
for (int sPre = 0; sPre < nTag; sPre++)
{
int f = _fGene.getEdgeFeatID(sPre, s);
YY[sPre, s] += w[f];
}
}
}
double maskValue = double.MinValue;
if (takeExp)
{
listTool.listExp(ref Y);
YY.eltExp();
maskValue = 0;
}
if (mask)
{
List <int> tagList = x.getTags();
for (int s = 0; s < Y.Count; s++)
{
if (tagList[i] != s)
{
Y[s] = maskValue;
}
}
}
}
virtual public void getLogYY(model m, dataSeq x, int i, ref dMatrix YY, ref List <double> Y, bool takeExp, bool mask)
{
YY.set(0);
listTool.listSet(ref Y, 0);
float[] w = m.W;
List <featureTemp> fList = _fGene.getFeatureTemp(x, i);
int nState = m.NState;
foreach (featureTemp ft in fList)
{
for (int s = 0; s < nState; s++)
{
int f = _fGene.getNodeFeatID(ft.id, s);
Y[s] += w[f] * ft.val;
}
}
if (i > 0)
{
for (int s = 0; s < nState; s++)
{
for (int sPre = 0; sPre < nState; sPre++)
{
int f = _fGene.getEdgeFeatID(sPre, s);
YY[sPre, s] += w[f];
}
}
}
double maskValue = double.MinValue;
if (takeExp)
{
listTool.listExp(ref Y);
YY.eltExp();
maskValue = 0;
}
if (mask)
{
dMatrix statesPerNodes = m.getStatesPerNode(x);
for (int s = 0; s < Y.Count; s++)
{
if (statesPerNodes[i, s] == 0)
{
Y[s] = maskValue;
}
}
}
}
virtual public double getGradCRF(List <double> vecGrad, model m, dataSeq x, baseHashSet <int> idSet)
{
if (idSet != null)
{
idSet.Clear();
}
int nTag = m.NTag;
//compute beliefs
belief bel = new belief(x.Count, nTag);
belief belMasked = new belief(x.Count, nTag);
//store the YY and Y
List <dMatrix> YYlist = new List <dMatrix>(), maskYYlist = new List <dMatrix>();
List <List <double> > Ylist = new List <List <double> >(), maskYlist = new List <List <double> >();
_inf.getYYandY(m, x, YYlist, Ylist, maskYYlist, maskYlist);
_inf.getBeliefs(bel, m, x, YYlist, Ylist);
_inf.getBeliefs(belMasked, m, x, maskYYlist, maskYlist);
double ZGold = belMasked.Z;
double Z = bel.Z;
List <featureTemp> fList;
//Loop over nodes to compute features and update the gradient
for (int i = 0; i < x.Count; i++)
{
fList = _fGene.getFeatureTemp(x, i);
foreach (featureTemp im in fList)
{
for (int s = 0; s < nTag; s++)
{
int f = _fGene.getNodeFeatID(im.id, s);
if (idSet != null)
{
idSet.Add(f);
}
vecGrad[f] += bel.belState[i][s] * im.val;
vecGrad[f] -= belMasked.belState[i][s] * im.val;
}
}
}
//Loop over edges to compute features and update the gradient
for (int i = 1; i < x.Count; i++)
{
for (int s = 0; s < nTag; s++)
{
for (int sPre = 0; sPre < nTag; sPre++)
{
int f = _fGene.getEdgeFeatID(sPre, s);
if (idSet != null)
{
idSet.Add(f);
}
vecGrad[f] += bel.belEdge[i][sPre, s];
vecGrad[f] -= belMasked.belEdge[i][sPre, s];
}
}
}
return(Z - ZGold);//-log{P(y*|x,w)}
}
public void getLogYY(model m, dataSeq x, int i, ref dMatrix YY, ref List <double> Y, bool takeExp, bool mask)
{
YY.set(0);
listTool.listSet(ref Y, 0);
float[] w = m.W;
List <featureTemp> fList = _fGene.getFeatureTemp(x, i);
int nTag = m.NTag;
//node feature
foreach (featureTemp im in fList)
{
nodeFeature[] features = Global.idNodeFeatures[im.id];
foreach (nodeFeature feat in features)
{
int f = feat._id;
int s = feat._s;
Y[s] += w[f] * im.val;
}
}
if (i > 0)
{
//non-rich edge
if (Global.useTraditionalEdge)
{
for (int s = 0; s < nTag; s++)
{
for (int sPre = 0; sPre < nTag; sPre++)
{
int f = _fGene.getEdgeFeatID(sPre, s);
YY[sPre, s] += w[f];
}
}
}
//rich edge
foreach (featureTemp im in fList)
{
edgeFeature[] features = Global.idEdgeFeatures[im.id];
foreach (edgeFeature feat in features)
{
YY[feat._sPre, feat._s] += w[feat._id] * im.val;
}
}
//rich2
if (Global.richFeat2)
{
List <featureTemp> fList2 = _fGene.getFeatureTemp(x, i - 1);
foreach (featureTemp im in fList2)
{
edgeFeature[] features = Global.idEdgeFeatures2[im.id];
foreach (edgeFeature feat in features)
{
YY[feat._sPre, feat._s] += w[feat._id] * im.val;
}
}
}
}
double maskValue = double.MinValue;
if (takeExp)
{
listTool.listExp(ref Y);
YY.eltExp();
maskValue = 0;
}
if (mask)
{
dMatrix statesPerNodes = m.getStatesPerNode(x);
for (int s = 0; s < Y.Count; s++)
{
if (statesPerNodes[i, s] == 0)
{
Y[s] = maskValue;
}
}
}
}