Method norm

trainer/utils.py:27–31

length-normalise LM score

(self)

        self.entries = {}

    def norm(self):
        "length-normalise LM score"
        for (k, _) in self.entries.items():
            labelingLen = len(self.entries[k].labeling)
            self.entries[k].prText = self.entries[k].prText ** (1.0 / (labelingLen if labelingLen else 1.0))

    def sort(self):
        "return beam-labelings, sorted by probability"