使用NLTK的BLEU对比两个完全相同句子无法得到1.0是什么原因

问题原因 #

你调用nltk.translate.bleu_score.sentence_bleu时第一个参数的传参格式不符合要求：
该方法的第一个参数需要接收参考译文集合，支持同时传入多条参考译文，每个参考译文本身是分词后的列表，因此入参格式是[reference_1_token_list, reference_2_token_list, ...]。你直接传入了单条分词后的参考列表，NLTK会误将每个独立单词识别为一条单独的参考句子，4-grams匹配完全失效，才会得到极低的异常评分。

修正后的代码 #

import nltk
from nltk import word_tokenize
from nltk.translate.bleu_score import SmoothingFunction
ref = 'You know that it would be untrue You know that I would be a liar If I was to say to you Girl, we couldnt get much higher.'
cand = 'You know that it would be untrue You know that I would be a liar If I was to say to you Girl, we couldnt get much higher.'
smoothie = SmoothingFunction().method1
reference = word_tokenize(ref)
candidate = word_tokenize(cand)
weights = (0.25, 0.25, 0.25, 0.25)
# 仅修改第一个参数为 [reference] 即可
BLEUscore = nltk.translate.bleu_score.sentence_bleu([reference], candidate, weights, smoothing_function=smoothie)
print(BLEUscore)

运行结果 #

修正后输出结果为1.0，符合相同句子BLEU评分取满分的预期，你选用的4-grams权重、method1平滑函数适配单句评估场景的设置没有其他问题。

内容的提问来源于stack exchange，提问作者slow_war