我已经在python中导入了nltk来计算ubuntu上的bleu分数。我理解句子级的bleu分数是如何工作的,但我不理解语料库级的bleu分数是如何工作的。
下面是我的语料库级BLeu分数代码:
import nltk
hypothesis = ['This', 'is', 'cat']
reference = ['This', 'is', 'a', 'cat']
BLEUscore = nltk.translate.bleu_score.corpus_bleu([reference], [hypothesis], weights = [1])
print(BLEUscore)
由于某种原因,上述代码的Bleu分数为0。我期望语料库水平的布鲁分数至少为0.5。
这是我的句子级BLeu分数代码
import nltk
hypothesis = ['This', 'is', 'cat']
reference = ['This', 'is', 'a', 'cat']
BLEUscore = nltk.translate.bleu_score.sentence_bleu([reference], hypothesis, weights = [1])
print(BLEUscore)
在这里,句子级别的bleu分数是0.71,这是我所期望的,考虑到简短的惩罚和漏掉的单词“a”。但是,我不理解语料库级别的BLEU评分是如何工作的。
任何帮助都将不胜感激。
最佳答案
DR:
>>> import nltk
>>> hypothesis = ['This', 'is', 'cat']
>>> reference = ['This', 'is', 'a', 'cat']
>>> references = [reference] # list of references for 1 sentence.
>>> list_of_references = [references] # list of references for all sentences in corpus.
>>> list_of_hypotheses = [hypothesis] # list of hypotheses that corresponds to list of references.
>>> nltk.translate.bleu_score.corpus_bleu(list_of_references, list_of_hypotheses)
0.6025286104785453
>>> nltk.translate.bleu_score.sentence_bleu(references, hypothesis)
0.6025286104785453
(注意:您必须在
develop
分支上提取最新版本的nltk,才能获得稳定版本的bleu score实现)长:
实际上,如果整个语料库中只有一个引用和一个假设,那么
corpus_bleu()
和sentence_bleu()
都应该返回与上面示例中所示相同的值。在代码中,我们看到:
def sentence_bleu(references, hypothesis, weights=(0.25, 0.25, 0.25, 0.25),
smoothing_function=None):
return corpus_bleu([references], [hypothesis], weights, smoothing_function)
如果我们看一下参数
def sentence_bleu(references, hypothesis, weights=(0.25, 0.25, 0.25, 0.25),
smoothing_function=None):
""""
:param references: reference sentences
:type references: list(list(str))
:param hypothesis: a hypothesis sentence
:type hypothesis: list(str)
:param weights: weights for unigrams, bigrams, trigrams and so on
:type weights: list(float)
:return: The sentence-level BLEU score.
:rtype: float
"""
sentence_bleu
引用的输入是acorpus_bleu
。因此,如果您有一个句子字符串,例如
sentence_bleu
,您必须对其进行标记以获取字符串列表,sentence_bleu
并且由于它允许多个引用,因此它必须是字符串列表,例如,如果您有第二个引用,“这是一只猫”,您输入到list(list(str))
的内容将是:references = [ ["This", "is", "a", "cat"], ["This", "is", "a", "feline"] ]
hypothesis = ["This", "is", "cat"]
sentence_bleu(references, hypothesis)
当涉及到“引用”参数的“列表”时,基本上是:
def corpus_bleu(list_of_references, hypotheses, weights=(0.25, 0.25, 0.25, 0.25),
smoothing_function=None):
"""
:param references: a corpus of lists of reference sentences, w.r.t. hypotheses
:type references: list(list(list(str)))
:param hypotheses: a list of hypothesis sentences
:type hypotheses: list(list(str))
:param weights: weights for unigrams, bigrams, trigrams and so on
:type weights: list(float)
:return: The corpus-level BLEU score.
:rtype: float
"""
除了查看
"This is a cat"
is actually a duck-type of ["This", "is", "a", "cat"]
中的doctest,您还可以查看a list of whatever the sentence_bleu()
takes as references中的unittest,以了解如何使用corpus_bleu()
中的每个组件。顺便说一下,由于在(
sentence_bleu()
>)(nltk/translate/bleu_score.py
)中将nltk/test/unit/translate/test_bleu_score.py
导入为bleu_score.py
,因此使用from nltk.translate import bleu
将与以下内容相同:
from nltk.translate.bleu_score import sentence_bleu
在代码中:
>>> from nltk.translate import bleu
>>> from nltk.translate.bleu_score import sentence_bleu
>>> from nltk.translate.bleu_score import corpus_bleu
>>> bleu == sentence_bleu
True
>>> bleu == corpus_bleu
False