Пример #1
0
 def __init__(self, name, makeString=True, wordVec=True, senna=True):
     if name.isdigit():
         self.name = name
         self.googleURL = name
     else:
         self.name = name
         self.googleURL = data.getGoogleURL(self)
     if makeString:
         self.string = data.getGoogleCase(self)
         tokenizer = linguistics.getTokenizer()
         self.tokens = tokenizer.tokenize(self.string)
         self.tokenSummary = {1:[], 2:[], 3:[], 4:[]}
         learning.readLabels([self], 'tokens')
         #if wordVec:
         #    self.representation = wordVector.getRepresentation(self)
         if senna:
             self.sennaMatrix = linguistics.getSennaMatrix(self)
             self.sentences = linguistics.getSennaAlignedSentences(self)
             self.srlSentences = linguistics.getSrlSentences(self)
             self.indicators = linguistics.resolveAnaphora(self)
             self.srlSummary = {1:[], 2:[], 3:[], 4:[]}
             learning.readLabels([self], 'srl')
Пример #2
0
                    if 'V' in clause and clause['V'] == word:
                        polyfitInput[0] += 1
                for clause in dm:
                    if 'A0' in clause and clause['A0'] == word:
                        polyfitInput[1] += 1
                    if 'V' in clause and clause['V'] == word:
                        polyfitInput[1] += 1
                print polyfitInput
                model[i] = np.polyfit([1, m], polyfitInput, 1)
            print model
    return findShortChains()

if __name__ == "__main__":
    cases = data.getAllSavedCases()
    labeledTraining = learning.findLabels(cases)
    learning.readLabels(labeledTraining)
    unlabeledCases = filter(lambda x:x not in labeledTraining, cases)
    unlabeledTraining = unlabeledCases[:-1]
    testing = [unlabeledCases[-1]]
    learning.labelCases(labeledTraining, unlabeledTraining, testing, numIterations=20)
    for cas in testing:
        print 'case ' + str(cas.name)
        d = {}
        for person, summarySentences in cas.summary.iteritems():
            personSentences = []
            for sentence in summarySentences:
                personSentences.append(cas.sentences[sentence])
            d[person] = personSentences
        for person, summarySentences in d.iteritems():
            print coherentSummary(summarySentences, cas.sentences, cas.srlSentences)
Пример #3
0
                for clause in dm:
                    if 'A0' in clause and clause['A0'] == word:
                        polyfitInput[1] += 1
                    if 'V' in clause and clause['V'] == word:
                        polyfitInput[1] += 1
                print polyfitInput
                model[i] = np.polyfit([1, m], polyfitInput, 1)
            print model

    return findShortChains()


if __name__ == "__main__":
    cases = data.getAllSavedCases()
    labeledTraining = learning.findLabels(cases)
    learning.readLabels(labeledTraining)
    unlabeledCases = filter(lambda x: x not in labeledTraining, cases)
    unlabeledTraining = unlabeledCases[:-1]
    testing = [unlabeledCases[-1]]
    learning.labelCases(labeledTraining,
                        unlabeledTraining,
                        testing,
                        numIterations=20)
    for cas in testing:
        print 'case ' + str(cas.name)
        d = {}
        for person, summarySentences in cas.summary.iteritems():
            personSentences = []
            for sentence in summarySentences:
                personSentences.append(cas.sentences[sentence])
            d[person] = personSentences