public virtual LexicalizedParser GetParserDataFromTreebank(Treebank trainTreebank)
{
log.Info("Binarizing training trees...");
IList <Tree> binaryTrainTrees = GetAnnotatedBinaryTreebankFromTreebank(trainTreebank);
Timing.Tick("done.");
IIndex <string> stateIndex = new HashIndex <string>();
log.Info("Extracting PCFG...");
IExtractor <Pair <UnaryGrammar, BinaryGrammar> > bgExtractor = new BinaryGrammarExtractor(op, stateIndex);
Pair <UnaryGrammar, BinaryGrammar> bgug = bgExtractor.Extract(binaryTrainTrees);
BinaryGrammar bg = bgug.second;
bg.SplitRules();
UnaryGrammar ug = bgug.first;
ug.PurgeRules();
Timing.Tick("done.");
log.Info("Extracting Lexicon...");
IIndex <string> wordIndex = new HashIndex <string>();
IIndex <string> tagIndex = new HashIndex <string>();
ILexicon lex = op.tlpParams.Lex(op, wordIndex, tagIndex);
lex.InitializeTraining(binaryTrainTrees.Count);
lex.Train(binaryTrainTrees);
lex.FinishTraining();
Timing.Tick("done.");
IExtractor <IDependencyGrammar> dgExtractor = op.tlpParams.DependencyGrammarExtractor(op, wordIndex, tagIndex);
IDependencyGrammar dg = null;
if (op.doDep)
{
log.Info("Extracting Dependencies...");
dg = dgExtractor.Extract(binaryTrainTrees);
dg.SetLexicon(lex);
Timing.Tick("done.");
}
log.Info("Done extracting grammars and lexicon.");
return(new LexicalizedParser(lex, bg, ug, dg, stateIndex, wordIndex, tagIndex, op));
}
internal LexicalizedParserQuery(LexicalizedParser parser)
{
this.op = parser.GetOp();
BinaryGrammar bg = parser.bg;
UnaryGrammar ug = parser.ug;
ILexicon lex = parser.lex;
IDependencyGrammar dg = parser.dg;
IIndex <string> stateIndex = parser.stateIndex;
IIndex <string> wordIndex = new DeltaIndex <string>(parser.wordIndex);
IIndex <string> tagIndex = parser.tagIndex;
this.debinarizer = new Debinarizer(op.forceCNF);
this.boundaryRemover = new BoundaryRemover();
if (op.doPCFG)
{
if (op.testOptions.iterativeCKY)
{
pparser = new IterativeCKYPCFGParser(bg, ug, lex, op, stateIndex, wordIndex, tagIndex);
}
else
{
pparser = new ExhaustivePCFGParser(bg, ug, lex, op, stateIndex, wordIndex, tagIndex);
}
}
else
{
pparser = null;
}
if (op.doDep)
{
dg.SetLexicon(lex);
if (!op.testOptions.useFastFactored)
{
dparser = new ExhaustiveDependencyParser(dg, lex, op, wordIndex, tagIndex);
}
else
{
dparser = null;
}
}
else
{
dparser = null;
}
if (op.doDep && op.doPCFG)
{
if (op.testOptions.useFastFactored)
{
MLEDependencyGrammar mledg = (MLEDependencyGrammar)dg;
int numToFind = 1;
if (op.testOptions.printFactoredKGood > 0)
{
numToFind = op.testOptions.printFactoredKGood;
}
bparser = new FastFactoredParser(pparser, mledg, op, numToFind, wordIndex, tagIndex);
}
else
{
IScorer scorer = new TwinScorer(pparser, dparser);
//Scorer scorer = parser;
if (op.testOptions.useN5)
{
bparser = new BiLexPCFGParser.N5BiLexPCFGParser(scorer, pparser, dparser, bg, ug, dg, lex, op, stateIndex, wordIndex, tagIndex);
}
else
{
bparser = new BiLexPCFGParser(scorer, pparser, dparser, bg, ug, dg, lex, op, stateIndex, wordIndex, tagIndex);
}
}
}
else
{
bparser = null;
}
subcategoryStripper = op.tlpParams.SubcategoryStripper();
}