public MLEDependencyGrammar(
TagProjection tagProjection,
TreebankLangParserParams tlpParams,
boolean directional,
boolean useDistance,
boolean useCoarseDistance,
Options op,
Index<String> wordIndex,
Index<String> tagIndex) {
super(
tlpParams.treebankLanguagePack(),
tagProjection,
directional,
useDistance,
useCoarseDistance,
op,
wordIndex,
tagIndex);
useSmoothTagProjection = op.useSmoothTagProjection;
useUnigramWordSmoothing = op.useUnigramWordSmoothing;
argCounter = new ClassicCounter<IntDependency>();
stopCounter = new ClassicCounter<IntDependency>();
double[] smoothParams = tlpParams.MLEDependencyGrammarSmoothingParams();
smooth_aT_hTWd = smoothParams[0];
smooth_aTW_hTWd = smoothParams[1];
smooth_stop = smoothParams[2];
interp = smoothParams[3];
// cdm added Jan 2007 to play with dep grammar smoothing. Integrate this better if we keep it!
smoothTP = new BasicCategoryTagProjection(tlpParams.treebankLanguagePack());
}
/**
* Determines method for print trees on output.
*
* @param tlpParams The treebank parser params
* @return A suitable tree printing object
*/
public TreePrint treePrint(TreebankLangParserParams tlpParams) {
TreebankLanguagePack tlp = tlpParams.treebankLanguagePack();
return new TreePrint(
outputFormat,
outputFormatOptions,
tlp,
tlpParams.headFinder(),
tlpParams.typedDependencyHeadFinder());
}
/** For testing: loads a treebank and prints the trees. */
public static void main(String[] args) {
TreebankLangParserParams tlpp = new ChineseTreebankParserParams();
System.out.println("Default encoding is: " + tlpp.diskTreebank().encoding());
if (args.length < 2) {
printlnErr(
"Usage: edu.stanford.nlp.parser.lexparser.ChineseTreebankParserParams treesPath fileRange");
} else {
Treebank m = tlpp.diskTreebank();
m.loadPath(args[0], new NumberRangesFileFilter(args[1], false));
for (Tree t : m) {
t.pennPrint(tlpp.pw());
}
System.out.println("There were " + m.size() + " trees.");
}
}
public TransformTreeDependency(TreebankLangParserParams tlpParams, boolean forceCNF) {
if (!Train.leftToRight) {
binarizer = new TreeAnnotatorAndBinarizer(tlpParams, forceCNF, !Train.outsideFactor(), true);
} else {
binarizer =
new TreeAnnotatorAndBinarizer(
tlpParams.headFinder(),
new LeftHeadFinder(),
tlpParams,
forceCNF,
!Train.outsideFactor(),
true);
}
if (Train.collinsPunc) {
collinsPuncTransformer = new CollinsPuncTransformer(tlpParams.treebankLanguagePack());
}
}
public MLEDependencyGrammar(
TreebankLangParserParams tlpParams,
boolean directional,
boolean distance,
boolean coarseDistance,
boolean basicCategoryTagsInDependencyGrammar,
Options op,
Index<String> wordIndex,
Index<String> tagIndex) {
this(
basicCategoryTagsInDependencyGrammar
? new BasicCategoryTagProjection(tlpParams.treebankLanguagePack())
: new TestTagProjection(),
tlpParams,
directional,
distance,
coarseDistance,
op,
wordIndex,
tagIndex);
}
