public static IList <Tree> BinarizeTreebank(Treebank treebank, Options op)
{
TreeBinarizer binarizer = TreeBinarizer.SimpleTreeBinarizer(op.tlpParams.HeadFinder(), op.tlpParams.TreebankLanguagePack());
BasicCategoryTreeTransformer basicTransformer = new BasicCategoryTreeTransformer(op.Langpack());
CompositeTreeTransformer transformer = new CompositeTreeTransformer();
transformer.AddTransformer(binarizer);
transformer.AddTransformer(basicTransformer);
treebank = treebank.Transform(transformer);
IHeadFinder binaryHeadFinder = new BinaryHeadFinder(op.tlpParams.HeadFinder());
IList <Tree> binarizedTrees = Generics.NewArrayList();
foreach (Tree tree in treebank)
{
Edu.Stanford.Nlp.Trees.Trees.ConvertToCoreLabels(tree);
tree.PercolateHeadAnnotations(binaryHeadFinder);
// Index from 1. Tools downstream expect index from 1, so for
// uses internal to the srparser we have to renormalize the
// indices, with the result that here we have to index from 1
tree.IndexLeaves(1, true);
binarizedTrees.Add(tree);
}
return(binarizedTrees);
}
public CacheParseHypotheses(LexicalizedParser parser)
{
treeBasicCategories = new BasicCategoryTreeTransformer(parser.TreebankLanguagePack());
treeFilter = new FilterConfusingRules(parser);
}
