bleu_score.py 文件源码

def modified_precision(references, hypothesis, n):
    # Extracts all ngrams in hypothesis
    # Set an empty Counter if hypothesis is empty.
    counts = Counter(ngrams(hypothesis, n)) if len(hypothesis) >= n else Counter()
    # Extract a union of references' counts.
    ## max_counts = reduce(or_, [Counter(ngrams(ref, n)) for ref in references])
    max_counts = {}
    for reference in references:
        reference_counts = Counter(ngrams(reference, n)) if len(reference) >= n else Counter()
        for ngram in counts:
            max_counts[ngram] = max(max_counts.get(ngram, 0),
                                    reference_counts[ngram])

    # Assigns the intersection between hypothesis and references' counts.
    clipped_counts = {ngram: min(count, max_counts[ngram])
                      for ngram, count in counts.items()}

    numerator = sum(clipped_counts.values())
    # Ensures that denominator is minimum 1 to avoid ZeroDivisionError.
    # Usually this happens when the ngram order is > len(reference).
    denominator = max(1, sum(counts.values()))

    return Fraction(numerator, denominator)