claim.py 文件源码

def determine_entities(self):
        """ Determines noun entities within a patent claim.
        param: pos - list of tuples from nltk pos tagger"""
        # Define grammar for chunking
        grammar = '''
            NP: {<DT|PRP\$> <VBG> <NN.*>+}
                {<DT|PRP\$> <NN.*> <POS> <JJ>* <NN.*>+}
                {<DT|PRP\$>? <JJ>* <NN.*>+ }
            '''
        cp = nltk.RegexpParser(grammar)
        # Or store as part of claim object property?

        # Option: split into features / clauses, run over clauses and
        # then re-correlate
        return cp.parse(self.pos)