问Bleu从零开始在蟒蛇比赛中得分

EN

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()))

0.27098211583470044
0.27098211583470044

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

rt_raw = [
'It is a guide to action that ensures that the military will forever heed Party commands',
'It is the guiding principle which guarantees the military forces always being under the command of the Party',
'It is the practical guide for the army always to heed the directions of the party'
]

ct_raw = [
'It is a guide to action which ensures that the military always obeys the commands of the party',
'It is to insure the troops forever hearing the activity guidebook that party direct'
]

def process_trans(t):
    return t.lower().split()

rt = [process_trans(t) for t in rt_raw]
ct = [process_trans(t) for t in ct_raw]

c1, c2 = ct[0], ct[1]

sentence_bleu_man(rt, c2, weights=(.5, .5, 0, 0))
sentence_bleu(rt, c2, weights=(.5, .5, 0, 0))

0.18174699151949172
0.18174699151949172

# coding: utf-8

import numpy as np
from collections import Counter
import math
from nltk.translate.bleu_score import sentence_bleu


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)

    # Clipped precision
    clipped_precision_score = []
    for ngram_level in range(1, 5):  # 1-gram to 4-gram
        
        
        original_ngram_list = n_gram_generator(original, ngram_level)
        original_n_gram = Counter(original_ngram_list)
        
        machine_ngram_list = n_gram_generator(machine_translated, ngram_level)
        machine_n_gram = Counter(machine_ngram_list)
        
        
        num_ngrams_in_translation = sum(machine_n_gram.values())  # number of ngrams in translation
        
        # iterate the unique ngrams in translation (candidate)
        for j in machine_n_gram:
            
            if j in original_n_gram:  # if found in reference
                
                if machine_n_gram[j] > original_n_gram[j]:  # CLIPPING - if found in translation more than in source, clip
                    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(float(sum(machine_n_gram.values())) / num_ngrams_in_translation)

    #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()))