Python LexicalizedParser Examples

Example #1

File: stanford_interface.py Project: danger89/stanford-parser-clientserver

    def __init__(self, parser_file = 'englishPCFG.ser.gz',
            parser_options=['-maxLength', '80', '-retainTmpSubcategories']):

        """@param parser_file: path to the serialised parser model
            (e.g. englishPCFG.ser.gz)
        @param parser_options: options
        """
        assert os.path.exists(parser_file)
        options = Options()
        options.setOptions(parser_options)
        self.lp = LexicalizedParser.getParserFromFile(parser_file, options)
        tlp = PennTreebankLanguagePack()
        self.gsf = tlp.grammaticalStructureFactory()
        self.lemmer = Morphology()
        self.word_token_factory = WordTokenFactory()
        self.parser_query = None

Example #2

    def __init__(self, parser_file,
            parser_options=['-maxLength', '80', '-retainTmpSubcategories']):

        """@param parser_file: path to the serialised parser model
            (e.g. englishPCFG.ser.gz)
        @param parser_options: options
        """

        assert os.path.exists(parser_file)
        options = Options()
        options.setOptions(parser_options)
        self.lp = LexicalizedParser.getParserFromFile(parser_file, options)
        tlp = PennTreebankLanguagePack()
        self.gsf = tlp.grammaticalStructureFactory()
        self.lemmer = Morphology()
        self.word_token_factory = WordTokenFactory()
        self.parser_query = None

Example #3

File: stanford_parser_server.py Project: sapresearch/fuzzy_adventure

import sys
import os
project_path = os.environ['FUZZY_ADVENTURE']
sys.path.append(project_path + '/external/stanford-parser-2012-07-09/stanford-parser.jar')
from java.io import CharArrayReader
from edu.stanford.nlp.parser.lexparser import LexicalizedParser
from edu.stanford.nlp import trees
from SimpleXMLRPCServer import SimpleXMLRPCServer

lp = LexicalizedParser.loadModel()

def tree(sentence):
	lp.setOptionFlags(["-maxLength", "80", "-retainTmpSubcategories"])

	tlp = trees.PennTreebankLanguagePack()
	toke = tlp.getTokenizerFactory().getTokenizer(CharArrayReader(sentence));
	wordlist = toke.tokenize()
	parse = lp.apply(wordlist)
			 
	gsf = tlp.grammaticalStructureFactory()
	gs = gsf.newGrammaticalStructure(parse)
	dependencies = gs.typedDependenciesCollapsed()

	parse = parse.toString()
	return parse#, dependencies


def tagged(sentence):
	lp.setOptionFlags(["-maxLength", "80", "-retainTmpSubcategories"])

	tlp = trees.PennTreebankLanguagePack()