List of collinizer() Examples

Examples of collinizer()

edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.collinizer()
The tree transformer used to produce trees for evaluation. It will be applied both to the parser output and the gold tree.
edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()
The tree transformer applied to trees prior to evaluation. For instance, it might delete punctuation nodes. This method will be applied both to the parse output tree and to the gold tree. The exact specification depends on "standard practice" for various treebanks. @return A TreeTransformer that performs adjustments to trees to deleteor equivalence class things not evaluated in the parser performance evaluation.

Examples of edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.collinizer()

    pwOut.println(goldTreebank.textualSummary());


    final String evalName = (tagMode) ? "TsarfatyTAG" : "TsarfatySEG";
    final TsarfatyEval eval = new TsarfatyEval(evalName, tagMode);


    final TreeTransformer tc = tlpp.collinizer();


    //PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
    //don't match, we need to keep looking for the next gold tree that matches.
    //The evalb ref implementation differs slightly as it expects one tree per line. It assigns
    //status as follows:

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final UnlabeledAttachmentEval metric = new UnlabeledAttachmentEval("UAS LP/LR", true, tlpp.headFinder());


    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.EnglishTreebankParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final TaggingEval metric = new TaggingEval("Tagging LP/LR");


    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final CollinsDepEval depEval = new CollinsDepEval("CollinsDep", true, tlpp.headFinder(), tlpp.treebankLanguagePack().startSymbol());


    final TreeTransformer tc = tlpp.collinizer();


    //PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
    //don't match, we need to keep looking for the next gold tree that matches.
    //The evalb ref implementation differs slightly as it expects one tree per line. It assigns
    //status as follows:

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println(goldTreebank.textualSummary());


    final String evalName = (tagMode) ? "TsarfatyTAG" : "TsarfatySEG";
    final TsarfatyEval eval = new TsarfatyEval(evalName, tagMode);


    final TreeTransformer tc = tlpp.collinizer();


    //PennTreeReader skips over null/malformed parses. So when the yields of the gold/guess trees
    //don't match, we need to keep looking for the next gold tree that matches.
    //The evalb ref implementation differs slightly as it expects one tree per line. It assigns
    //status as follows:

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final LeafAncestorEval metric = new LeafAncestorEval("LeafAncestor");


    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final UnlabeledAttachmentEval metric = new UnlabeledAttachmentEval("UAS LP/LR", true, tlpp.headFinder());


    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final TaggingEval metric = new TaggingEval("Tagging LP/LR");


    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

Examples of edu.stanford.nlp.parser.lexparser.TreebankLangParserParams.collinizer()

    pwOut.println("GOLD TREEBANK:");
    pwOut.println(goldTreebank.textualSummary());


    final Evalb metric = new Evalb("Evalb LP/LR", true);
    final EvalbByCat evalbCat = (doCatLevel) ? new EvalbByCat("EvalbByCat LP/LR", true, labelRegex) : null;
    final TreeTransformer tc = tlpp.collinizer();


    //The evalb ref implementation assigns status for each tree pair as follows:
    //
    //   0 - Ok (yields match)
    //   1 - length mismatch

View Full Code Here

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.