从零开始在python中获得Bleu分数

Question

在观看Andrew Ng关于Bleu score的视频后，我想在Python中从头开始实现一个。我用python和numpy编写了完整的代码。这是完整的代码

import numpy as np

def n_gram_generator(sentence,n= 2,n_gram= False):
    '''
    N-Gram generator with parameters sentence
    n is for number of n_grams
    The n_gram parameter removes repeating n_grams 
    '''
    sentence = sentence.lower() # converting to lower case
    sent_arr = np.array(sentence.split()) # split to string arrays
    length = len(sent_arr)

    word_list = []
    for i in range(length+1):
        if i < n:
            continue
        word_range = list(range(i-n,i))
        s_list = sent_arr[word_range]
        string = ' '.join(s_list) # converting list to strings
        word_list.append(string) # append to word_list
        if n_gram:
            word_list = list(set(word_list))
    return word_list

def bleu_score(original,machine_translated):
    '''
    Bleu score function given a orginal and a machine translated sentences
    '''
    mt_length = len(machine_translated.split())
    o_length = len(original.split())

    # Brevity Penalty 
    if mt_length>o_length:
        BP=1
    else:
        penality=1-(mt_length/o_length)
        BP=np.exp(penality)

    # calculating precision
    precision_score = []
    for i in range(mt_length):
        original_n_gram = n_gram_generator(original,i)
        machine_n_gram = n_gram_generator(machine_translated,i)
        n_gram_list = list(set(machine_n_gram)) # removes repeating strings

        # counting number of occurence 
        machine_score = 0
        original_score = 0
        for j in n_gram_list:
            machine_count = machine_n_gram.count(j)
            original_count = original_n_gram.count(j)
            machine_score = machine_score+machine_count
            original_score = original_score+original_count

        precision = original_score/machine_score
        precision_score.append(precision)
    precisions_sum = np.array(precision_score).sum()
    avg_precisions_sum=precisions_sum/mt_length
    bleu=BP*np.exp(avg_precisions_sum)
    return bleu

if __name__ == "__main__":
    original = "this is a test"
    bs=bleu_score(original,original)
    print("Bleu Score Original",bs)

我试着用nltk测试我的分数

^{pr2}$

问题是我的bleu分数是2.718281，nltk是1。我做错什么了？在

以下是一些可能的原因：

1）我根据机器翻译的句子长度计算了ngrams。从1点到4点

2）n_gram_generator我自己写的函数，不确定它的准确性

3）一些我如何使用错误的函数或计算错误的bleu分数

有人能查一下我的密码，告诉我哪里出错了吗？在

Answer 1

以下是实际^{cd1>}source code的稍微修改版本：

def sentence_bleu_man(
    references,
    hypothesis,
    weights=(0.25, 0.25, 0.25, 0.25)):

    # compute modified precision for 1-4 ngrams
    p_numerators = Counter()  
    p_denominators = Counter()  
    hyp_lengths, ref_lengths = 0, 0

    for i, _ in enumerate(weights, start=1):
        p_i = modified_precision(references, hypothesis, i)
        p_numerators[i] += p_i.numerator
        p_denominators[i] += p_i.denominator

    # compute brevity penalty    
    hyp_len = len(hypothesis)
    ref_len = closest_ref_length(references, hyp_len)
    bp = brevity_penalty(ref_len, hyp_len)

    # compute final score
    p_n = [
        Fraction(p_numerators[i], p_denominators[i], 
        _normalize=False)
        for i, _ in enumerate(weights, start=1)
        if p_numerators[i] > 0
    ]
    s = (w_i * math.log(p_i) for w_i, p_i in zip(weights, p_n))
    s = bp * math.exp(math.fsum(s))

    return s

我们可以使用原始paper中的示例：

^{pr2}$

输出：

^{pr3}$

Answer 2

你的bleu分数计算错误。 发行日期：

• 你必须使用精确剪裁
• sklearn使用每个n克的权重
• sklearn使用n=1,2,3,4的ngrams

更正代码

def bleu_score(original,machine_translated):
    '''
    Bleu score function given a orginal and a machine translated sentences
    '''
    mt_length = len(machine_translated.split())
    o_length = len(original.split())

    # Brevity Penalty 
    if mt_length>o_length:
        BP=1
    else:
        penality=1-(mt_length/o_length)
        BP=np.exp(penality)

    # Clipped precision
    clipped_precision_score = []
    for i in range(1, 5):
        original_n_gram = Counter(n_gram_generator(original,i))
        machine_n_gram = Counter(n_gram_generator(machine_translated,i))

        c = sum(machine_n_gram.values())
        for j in machine_n_gram:
            if j in original_n_gram:
                if machine_n_gram[j] > original_n_gram[j]:
                    machine_n_gram[j] = original_n_gram[j]
            else:
                machine_n_gram[j] = 0

        #print (sum(machine_n_gram.values()), c)
        clipped_precision_score.append(sum(machine_n_gram.values())/c)

    #print (clipped_precision_score)

    weights =[0.25]*4

    s = (w_i * math.log(p_i) for w_i, p_i in zip(weights, clipped_precision_score))
    s = BP * math.exp(math.fsum(s))
    return s

original = "It is a guide to action which ensures that the military alwasy obeys the command of the party"
machine_translated = "It is the guiding principle which guarantees the military forces alwasy being under the command of the party"

print (bleu_score(original, machine_translated))
print (sentence_bleu([original.split()], machine_translated.split()))

输出：

^{pr2}$