public DependencyParser(int order, string modelFileName, bool createForest)
{
DependencyPipe pipe = order == 2 ? new DependencyPipe2O(true) : new DependencyPipe(true);
pipe.setLabel(createForest);
m_pipe = pipe;
m_params = new Parameters(pipe.DataAlphabet.Count);
m_decoder = SecondOrder ? new DependencyDecoder2O(pipe) : new DependencyDecoder(pipe);
LoadModel(modelFileName);
pipe.CloseAlphabets();
}
public DependencyParser(DependencyPipe pipe)
{
m_pipe = pipe;
m_params = new Parameters(pipe.DataAlphabet.Count);
m_decoder = SecondOrder ? new DependencyDecoder2O(pipe) : new DependencyDecoder(pipe);
}
// TODO: sina: rename it to ReadFeatureVector
public DependencyInstance GetFeatureVector(BinaryReader reader,
DependencyInstance inst,
FeatureVector[,,] fvs,
double[,,] probs,
FeatureVector[,,] fvsTrips,
double[,,] probsTrips,
FeatureVector[,,] fvsSibs,
double[,,] probsSibs,
FeatureVector[,,,] ntFvs,
double[,,,] ntProbs,
Parameters @params)
{
int length = inst.Length;
// Get production crap.
for (int w1 = 0; w1 < length; w1++)
{
for (int w2 = w1 + 1; w2 < length; w2++)
{
for (int ph = 0; ph < 2; ph++)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double prodProb = @params.GetScore(prodFV);
fvs[w1, w2, ph] = prodFV;
probs[w1, w2, ph] = prodProb;
}
}
}
int last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
if (Labeled)
{
for (int w1 = 0; w1 < length; w1++)
{
for (int t = 0; t < Types.Length; t++)
{
string type = Types[t];
for (int ph = 0; ph < 2; ph++)
{
for (int ch = 0; ch < 2; ch++)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double ntProb = @params.GetScore(prodFV);
ntFvs[w1, t, ph, ch] = prodFV;
ntProbs[w1, t, ph, ch] = ntProb;
}
}
}
}
last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
}
for (int w1 = 0; w1 < length; w1++)
{
for (int w2 = w1; w2 < length; w2++)
{
for (int w3 = w2 + 1; w3 < length; w3++)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double prodProb = @params.GetScore(prodFV);
fvsTrips[w1, w2, w3] = prodFV;
probsTrips[w1, w2, w3] = prodProb;
}
}
for (int w2 = w1; w2 >= 0; w2--)
{
for (int w3 = w2 - 1; w3 >= 0; w3--)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double prodProb = @params.GetScore(prodFV);
fvsTrips[w1, w2, w3] = prodFV;
probsTrips[w1, w2, w3] = prodProb;
}
}
}
last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
for (int w1 = 0; w1 < length; w1++)
{
for (int w2 = 0; w2 < length; w2++)
{
for (int wh = 0; wh < 2; wh++)
{
if (w1 != w2)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double prodProb = @params.GetScore(prodFV);
fvsSibs[w1, w2, wh] = prodFV;
probsSibs[w1, w2, wh] = prodProb;
}
}
}
}
last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
var nfv = new FeatureVector();
int next = reader.ReadInt32();
while (next != -4)
{
AddNewFeature(next, 1.0, nfv);
next = reader.ReadInt32();
}
string[] toks = null;
string[] pos = null;
string[] labs = null;
string actParseTree = null;
try
{
int len = reader.ReadInt32(); //Added by MSR
toks = new string[len];
for (int i = 0; i < len; i++)
{
toks[i] = reader.ReadString();
}
//next = reader.ReadInt32();
len = reader.ReadInt32(); //Added by MSR
pos = new string[len];
for (int i = 0; i < len; i++)
{
pos[i] = reader.ReadString();
}
next = reader.ReadInt32();
len = reader.ReadInt32(); //Added by MSR
labs = new string[len];
for (int i = 0; i < len; i++)
{
labs[i] = reader.ReadString();
}
next = reader.ReadInt32();
actParseTree = reader.ReadString();
next = reader.ReadInt32();
}
catch (Exception e)
{
// TODO: sina: A library MUST NOT call Environment.Exit in any form
// throw exception instead.
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
if (next != -1)
{
// TODO: sina: A library MUST NOT call Environment.Exit in any form
// throw exception instead.
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
var pti = new DependencyInstance(toks, pos, labs, nfv);
pti.ActParseTree = actParseTree;
return pti;
}
public void GetFeatureVector(DependencyInstance inst,
FeatureVector[,,] fvs,
double[,,] probs,
FeatureVector[,,] fvsTrips,
double[,,] probsTrips,
FeatureVector[,,] fvsSibs,
double[,,] probsSibs,
FeatureVector[,,,] ntFvs,
double[,,,] ntProbs, Parameters @params)
{
string[] toks = inst.Sentence;
string[] pos = inst.POS;
string[] labs = inst.Labs;
var posA = new string[pos.Length];
for (int i = 0; i < pos.Length; i++)
{
posA[i] = pos[i].SubstringWithIndex(0, 1);
}
// Get production crap.
for (int w1 = 0; w1 < toks.Length; w1++)
{
for (int w2 = w1 + 1; w2 < toks.Length; w2++)
{
for (int ph = 0; ph < 2; ph++)
{
bool attR = ph == 0 ? true : false;
int childInt = attR ? w2 : w1;
int parInt = attR ? w1 : w2;
FeatureVector prodFV = CreateFeatureVector(toks, pos, posA, w1, w2, attR,
new FeatureVector());
double prodProb = @params.GetScore(prodFV);
fvs[w1, w2, ph] = prodFV;
probs[w1, w2, ph] = prodProb;
}
}
}
if (Labeled)
{
for (int w1 = 0; w1 < toks.Length; w1++)
{
for (int t = 0; t < Types.Length; t++)
{
string type = Types[t];
for (int ph = 0; ph < 2; ph++)
{
bool attR = ph == 0 ? true : false;
for (int ch = 0; ch < 2; ch++)
{
bool child = ch == 0 ? true : false;
FeatureVector prodFV = CreateFeatureVector(toks, pos, posA, w1,
type, attR, child,
new FeatureVector());
double ntProb = @params.GetScore(prodFV);
ntFvs[w1, t, ph, ch] = prodFV;
ntProbs[w1, t, ph, ch] = ntProb;
}
}
}
}
}
for (int w1 = 0; w1 < toks.Length; w1++)
{
for (int w2 = w1; w2 < toks.Length; w2++)
{
for (int w3 = w2 + 1; w3 < toks.Length; w3++)
{
FeatureVector prodFV = CreateFeatureVector(toks, pos, posA, w1, w2, w3,
new FeatureVector());
double prodProb = @params.GetScore(prodFV);
fvsTrips[w1, w2, w3] = prodFV;
probsTrips[w1, w2, w3] = prodProb;
}
}
for (int w2 = w1; w2 >= 0; w2--)
{
for (int w3 = w2 - 1; w3 >= 0; w3--)
{
FeatureVector prodFV = CreateFeatureVector(toks, pos, posA, w1, w2, w3,
new FeatureVector());
double prodProb = @params.GetScore(prodFV);
fvsTrips[w1, w2, w3] = prodFV;
probsTrips[w1, w2, w3] = prodProb;
}
}
}
for (int w1 = 0; w1 < toks.Length; w1++)
{
for (int w2 = 0; w2 < toks.Length; w2++)
{
for (int wh = 0; wh < 2; wh++)
{
if (w1 != w2)
{
FeatureVector prodFV = CreateFeatureVectorSib(toks, pos, w1, w2, wh == 0,
new FeatureVector());
double prodProb = @params.GetScore(prodFV);
fvsSibs[w1, w2, wh] = prodFV;
probsSibs[w1, w2, wh] = prodProb;
}
}
}
}
}
public DependencyInstance ReadFeatureVector(BinaryReader reader,
DependencyInstance inst,
FeatureVector[,,] fvs,
double[,,] probs,
FeatureVector[,,,] ntFvs,
double[,,,] ntProbs,
Parameters parameters)
{
int length = inst.Length;
// Get production crap.
for (int w1 = 0; w1 < length; w1++)
{
for (int w2 = w1 + 1; w2 < length; w2++)
{
for (int ph = 0; ph < 2; ph++)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double prodProb = parameters.GetScore(prodFV);
fvs[w1, w2, ph] = prodFV;
probs[w1, w2, ph] = prodProb;
}
}
}
int last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
if (Labeled)
{
for (int w1 = 0; w1 < length; w1++)
{
for (int t = 0; t < Types.Length; t++)
{
string type = Types[t];
for (int ph = 0; ph < 2; ph++)
{
for (int ch = 0; ch < 2; ch++)
{
var prodFV = new FeatureVector();
int indx = reader.ReadInt32();
while (indx != -2)
{
AddNewFeature(indx, 1.0, prodFV);
indx = reader.ReadInt32();
}
double ntProb = parameters.GetScore(prodFV);
ntFvs[w1, t, ph, ch] = prodFV;
ntProbs[w1, t, ph, ch] = ntProb;
}
}
}
}
last = reader.ReadInt32();
if (last != -3)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
}
var nfv = new FeatureVector();
int next = reader.ReadInt32();
while (next != -4)
{
AddNewFeature(next, 1.0, nfv);
next = reader.ReadInt32();
}
string[] toks = null;
string[] pos = null;
string[] labs = null;
string actParseTree = null;
try
{
int len = reader.ReadInt32();
toks = new string[len];
for (int i = 0; i < len; i++)
{
toks[i] = reader.ReadString();
}
next = reader.ReadInt32();
len = reader.ReadInt32();
pos = new string[len];
for (int i = 0; i < len; i++)
{
pos[i] = reader.ReadString();
}
next = reader.ReadInt32();
len = reader.ReadInt32();
labs = new string[len];
for (int i = 0; i < len; i++)
{
labs[i] = reader.ReadString();
}
next = reader.ReadInt32();
actParseTree = reader.ReadString();
next = reader.ReadInt32();
}
catch (Exception e)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
if (next != -1)
{
Console.WriteLine("Error reading file.");
throw new Exception("Bad File Format");
}
var pti = new DependencyInstance(toks, pos, labs, nfv);
pti.ActParseTree = actParseTree;
return pti;
}