bleu.py

"""
@author : Hyunwoong
@when : 2019-12-22
@homepage : https://github.com/gusdnd852
"""
import math
from collections import Counter

import numpy as np


def bleu_stats(hypothesis, reference):
    """Compute statistics for BLEU."""
    stats = []
    stats.append(len(hypothesis))
    stats.append(len(reference))
    for n in range(1, 5):
        s_ngrams = Counter(
            [tuple(hypothesis[i:i + n]) for i in range(len(hypothesis) + 1 - n)]
        )
        r_ngrams = Counter(
            [tuple(reference[i:i + n]) for i in range(len(reference) + 1 - n)]
        )

        stats.append(max([sum((s_ngrams & r_ngrams).values()), 0]))
        stats.append(max([len(hypothesis) + 1 - n, 0]))
    return stats


def bleu(stats):
    """Compute BLEU given n-gram statistics."""
    if len(list(filter(lambda x: x == 0, stats))) > 0:
        return 0
    (c, r) = stats[:2]
    log_bleu_prec = sum(
        [math.log(float(x) / y) for x, y in zip(stats[2::2], stats[3::2])]
    ) / 4.
    return math.exp(min([0, 1 - float(r) / c]) + log_bleu_prec)


def get_bleu(hypotheses, reference):
    """Get validation BLEU score for dev set."""
    stats = np.array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
    for hyp, ref in zip(hypotheses, reference):
        stats += np.array(bleu_stats(hyp, ref))
    return 100 * bleu(stats)


def idx_to_word(x, vocab):
    words = []
    for i in x:
        word = vocab.itos[i]
        if '<' not in word:
            words.append(word)
    words = " ".join(words)
    return words