Esempio n. 1
0
 def getInterestingLabel(self, treeNode):
     """
     Finds 'interesting things' such as inversions, shifters,
     etc.
     """
     if len(treeNode) < 2:
         return None
     if self.granularity == ma_util.GRANULARITY_COARSE:
         raise NotImplementedError(
             'getInterestingLabels does not handle coarse labels!')
     catP = ma_util.sen(treeNode.node, self.granularity)
     catL = ma_util.sen(treeNode[0].node, self.granularity)
     catR = ma_util.sen(treeNode[1].node, self.granularity)
     if catP == catL and catP == catR:
         return "ID"
     cat_max = max(catL, catR)
     cat_min = min(catL, catR)
     cat_avg = (catL + catR) / 2.0
     # cat_miv is low if max sentiment is very POS
     cat_miv = ma_util.VERY_POS - cat_max
     # cat_mav is low if min sentiment is very POS
     cat_mav = ma_util.VERY_POS - cat_min
     if catP <= cat_max and catP >= cat_min:
         r_label = 'AVG'
     # is parent less positive than most positive child
     # and more positive than least positive?
     elif catP <= cat_mav and catP >= cat_miv:
         r_label = 'INV'
     elif catL == ma_util.FINE_NEU and ((catP - ma_util.FINE_NEU)
                                        * (catR - ma_util.FINE_NEU) < 0):
         #r_label = 'INV/L'
         r_label = 'INV'
     elif catR == ma_util.FINE_NEU and ((catP - ma_util.FINE_NEU)
                                        * (catL - ma_util.FINE_NEU) < 0):
         #r_label = 'INV/R'
         r_label = 'INV'
     elif (catP - ma_util.FINE_NEU) * (cat_avg - ma_util.FINE_NEU) > 0:
         # (3 (4 wundervollen) (2 Szenen)) would match
         # here, but other rules fire first
         # Also not sure if there is intensification happening there?
         r_label = 'INT'
     else:
         #r_label = '???'
         r_label = "MWE"
     return r_label
Esempio n. 2
0
 def getProduction(self, treeNode):
     """
     >>> pe = ProdEvaluator()
     >>> from nltk.tree import Tree
     >>> t = Tree(3, [Tree(3, "good"), Tree(2, "movie")])
     >>> pe.getProduction(t)
     (3,3,2)
     >>> t = Tree(3, "good")
     >>> pe.getProduction(t)
     None
     """
     # If the tree is binary, then its children are other tree instances
     # unary nodes only have for terminals and associated sentiment label
     if len(treeNode) < 2:
         return None
     top = ma_util.sen(treeNode.node, self.granularity)
     c0 = ma_util.sen(treeNode[0].node, self.granularity)
     c1 = ma_util.sen(treeNode[1].node, self.granularity)
     return (top, c0, c1)
Esempio n. 3
0
    def extract_projection_sentiment(self, tigerObj, tigerSentence):
        """Extracts projection feature.

        @param tigerObj {TigerXML} Full parse file
        @param tigerSentence {some XML Element} XML node of current sentence
        @returns {list} Sentiment Values for each Span NEG, NEU, POS
        """
        data = []
        for node in tigerObj.preOrder(tigerSentence, forceSentiment=True):
            data.append(ma_util.sen(node[1], self.granularity))
        return data
Esempio n. 4
0
    def extract_gold_sentiment(self, goldSentence, extractLength=False):
        """Extracts gold label.

        @param goldSentence {PTB tree} Parse tree with sentiment annotation
        @returns {list} List of labels
        """
        data = []
        for goldNode in ma_util.walkTree(goldSentence):
            label = ma_util.sen(goldNode.node, self.granularity)
            if extractLength:
                data.append((label, len(goldNode.leaves())))
            else:
                data.append(label)
        return data