Package edu.stanford.nlp.trees.international.pennchinese

Class Summary
BikelChineseHeadFinder A headfinder implementing Dan Bikel's head rules.
CharacterLevelTagExtender A transformer to extend tags down to the level of individual characters.
ChineseCollinizer Performs collinization operations on Chinese trees similar to those for English Namely: strips all functional & automatically-added tags strips all punctuation merges PRN and ADVP eliminates ROOT (note that there are a few non-unary ROOT nodes; these are not eliminated)
ChineseEnglishWordMap A class for mapping Chinese words to English.
ChineseEscaper An Escaper for Chinese normalization to match Treebank.
ChineseHeadFinder HeadFinder for the Penn Chinese Treebank.
ChineseSemanticHeadFinder Implements a 'semantic head' variant of the the HeadFinder found in Chinese Head Finder
ChineseTreebankLanguagePack Language pack for the UPenn/Colorado Chinese treebank.
CHTBTokenizer A simple tokenizer for tokenizing Penn Chinese Treebank files.
CTBErrorCorrectingTreeNormalizer This was originally written to correct a few errors Galen found in CTB3.
CTBTreeReaderFactory The CTBTreeReaderFactory is a factory for creating a TreeReader suitable for the Penn CTB.
FragDiscardingPennTreeReader  
NoEmptiesCTBTreeReaderFactory A CTB TreeReaderFactory that deletes empty nodes.
RadicalMap A way to determine the primary (or "semantic") radical of a Chinese character or get the set of characters with a given semantic radical.
SunJurafskyChineseHeadFinder A headfinder for Chinese based on rules described in Sun/Jurafsky NAACL '04.
 



Stanford NLP Group