def _compute()

in metrics/bleu/bleu.py [0:0]

• 17 lines of code
• 7 McCabe index (conditional complexity)

    def _compute(self, predictions, references, tokenizer=Tokenizer13a(), max_order=4, smooth=False):
        # if only one reference is provided make sure we still use list of lists
        if isinstance(references[0], str):
            references = [[ref] for ref in references]

        references = [[tokenizer(r) for r in ref] for ref in references]
        predictions = [tokenizer(p) for p in predictions]
        score = compute_bleu(
            reference_corpus=references, translation_corpus=predictions, max_order=max_order, smooth=smooth
        )
        (bleu, precisions, bp, ratio, translation_length, reference_length) = score
        return {
            "bleu": bleu,
            "precisions": precisions,
            "brevity_penalty": bp,
            "length_ratio": ratio,
            "translation_length": translation_length,
            "reference_length": reference_length,
        }