nltk.translate.bleu_score module

BLEU score implementation.

class nltk.translate.bleu_score.SmoothingFunction[source]

Bases: object

This is an implementation of the smoothing techniques for segment-level BLEU scores that was presented in Boxing Chen and Collin Cherry (2014) A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU. In WMT14. http://acl2014.org/acl2014/W14-33/pdf/W14-3346.pdf

__init__(epsilon=0.1, alpha=5, k=5)[source]

This will initialize the parameters required for the various smoothing techniques, the default values are set to the numbers used in the experiments from Chen and Cherry (2014).

>>> hypothesis1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'which', 'ensures',
...                 'that', 'the', 'military', 'always', 'obeys', 'the',
...                 'commands', 'of', 'the', 'party']
>>> reference1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'that', 'ensures',
...               'that', 'the', 'military', 'will', 'forever', 'heed',
...               'Party', 'commands']
>>> chencherry = SmoothingFunction()
>>> print(sentence_bleu([reference1], hypothesis1)) 
0.4118...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method0)) 
0.4118...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method1)) 
0.4118...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method2)) 
0.4452...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method3)) 
0.4118...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method4)) 
0.4118...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method5)) 
0.4905...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method6)) 
0.4135...
>>> print(sentence_bleu([reference1], hypothesis1, smoothing_function=chencherry.method7)) 
0.4905...
Parameters
  • epsilon (float) – the epsilon value use in method 1

  • alpha (int) – the alpha value use in method 6

  • k (int) – the k value use in method 4

method0(p_n, *args, **kwargs)[source]

No smoothing.

method1(p_n, *args, **kwargs)[source]

Smoothing method 1: Add epsilon counts to precision with 0 counts.

method2(p_n, *args, **kwargs)[source]

Smoothing method 2: Add 1 to both numerator and denominator from Chin-Yew Lin and Franz Josef Och (2004) ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation. In COLING 2004.

method3(p_n, *args, **kwargs)[source]

Smoothing method 3: NIST geometric sequence smoothing The smoothing is computed by taking 1 / ( 2^k ), instead of 0, for each precision score whose matching n-gram count is null. k is 1 for the first ‘n’ value for which the n-gram match count is null/

For example, if the text contains:

  • one 2-gram match

  • and (consequently) two 1-gram matches

the n-gram count for each individual precision score would be:

  • n=1 => prec_count = 2 (two unigrams)

  • n=2 => prec_count = 1 (one bigram)

  • n=3 => prec_count = 1/2 (no trigram, taking ‘smoothed’ value of 1 / ( 2^k ), with k=1)

  • n=4 => prec_count = 1/4 (no fourgram, taking ‘smoothed’ value of 1 / ( 2^k ), with k=2)

method4(p_n, references, hypothesis, hyp_len=None, *args, **kwargs)[source]

Smoothing method 4: Shorter translations may have inflated precision values due to having smaller denominators; therefore, we give them proportionally smaller smoothed counts. Instead of scaling to 1/(2^k), Chen and Cherry suggests dividing by 1/ln(len(T)), where T is the length of the translation.

method5(p_n, references, hypothesis, hyp_len=None, *args, **kwargs)[source]

Smoothing method 5: The matched counts for similar values of n should be similar. To a calculate the n-gram matched count, it averages the n−1, n and n+1 gram matched counts.

method6(p_n, references, hypothesis, hyp_len=None, *args, **kwargs)[source]

Smoothing method 6: Interpolates the maximum likelihood estimate of the precision p_n with a prior estimate pi0. The prior is estimated by assuming that the ratio between pn and pn−1 will be the same as that between pn−1 and pn−2; from Gao and He (2013) Training MRF-Based Phrase Translation Models using Gradient Ascent. In NAACL.

method7(p_n, references, hypothesis, hyp_len=None, *args, **kwargs)[source]

Smoothing method 7: Interpolates methods 4 and 5.

nltk.translate.bleu_score.brevity_penalty(closest_ref_len, hyp_len)[source]

Calculate brevity penalty.

As the modified n-gram precision still has the problem from the short length sentence, brevity penalty is used to modify the overall BLEU score according to length.

An example from the paper. There are three references with length 12, 15 and 17. And a concise hypothesis of the length 12. The brevity penalty is 1.

>>> reference1 = list('aaaaaaaaaaaa')      # i.e. ['a'] * 12
>>> reference2 = list('aaaaaaaaaaaaaaa')   # i.e. ['a'] * 15
>>> reference3 = list('aaaaaaaaaaaaaaaaa') # i.e. ['a'] * 17
>>> hypothesis = list('aaaaaaaaaaaa')      # i.e. ['a'] * 12
>>> references = [reference1, reference2, reference3]
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> brevity_penalty(closest_ref_len, hyp_len)
1.0

In case a hypothesis translation is shorter than the references, penalty is applied.

>>> references = [['a'] * 28, ['a'] * 28]
>>> hypothesis = ['a'] * 12
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> brevity_penalty(closest_ref_len, hyp_len)
0.2635971381157267

The length of the closest reference is used to compute the penalty. If the length of a hypothesis is 12, and the reference lengths are 13 and 2, the penalty is applied because the hypothesis length (12) is less then the closest reference length (13).

>>> references = [['a'] * 13, ['a'] * 2]
>>> hypothesis = ['a'] * 12
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> brevity_penalty(closest_ref_len, hyp_len) 
0.9200...

The brevity penalty doesn’t depend on reference order. More importantly, when two reference sentences are at the same distance, the shortest reference sentence length is used.

>>> references = [['a'] * 13, ['a'] * 11]
>>> hypothesis = ['a'] * 12
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> bp1 = brevity_penalty(closest_ref_len, hyp_len)
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(reversed(references), hyp_len)
>>> bp2 = brevity_penalty(closest_ref_len, hyp_len)
>>> bp1 == bp2 == 1
True

A test example from mteval-v13a.pl (starting from the line 705):

>>> references = [['a'] * 11, ['a'] * 8]
>>> hypothesis = ['a'] * 7
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> brevity_penalty(closest_ref_len, hyp_len) 
0.8668...
>>> references = [['a'] * 11, ['a'] * 8, ['a'] * 6, ['a'] * 7]
>>> hypothesis = ['a'] * 7
>>> hyp_len = len(hypothesis)
>>> closest_ref_len =  closest_ref_length(references, hyp_len)
>>> brevity_penalty(closest_ref_len, hyp_len)
1.0
Parameters
  • hyp_len (int) – The length of the hypothesis for a single sentence OR the sum of all the hypotheses’ lengths for a corpus

  • closest_ref_len (int) – The length of the closest reference for a single hypothesis OR the sum of all the closest references for every hypotheses.

Returns

BLEU’s brevity penalty.

Return type

float

nltk.translate.bleu_score.closest_ref_length(references, hyp_len)[source]

This function finds the reference that is the closest length to the hypothesis. The closest reference length is referred to as r variable from the brevity penalty formula in Papineni et. al. (2002)

Parameters
  • references (list(list(str))) – A list of reference translations.

  • hyp_len (int) – The length of the hypothesis.

Returns

The length of the reference that’s closest to the hypothesis.

Return type

int

nltk.translate.bleu_score.corpus_bleu(list_of_references, hypotheses, weights=(0.25, 0.25, 0.25, 0.25), smoothing_function=None, auto_reweigh=False)[source]

Calculate a single corpus-level BLEU score (aka. system-level BLEU) for all the hypotheses and their respective references.

Instead of averaging the sentence level BLEU scores (i.e. macro-average precision), the original BLEU metric (Papineni et al. 2002) accounts for the micro-average precision (i.e. summing the numerators and denominators for each hypothesis-reference(s) pairs before the division).

>>> hyp1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'which',
...         'ensures', 'that', 'the', 'military', 'always',
...         'obeys', 'the', 'commands', 'of', 'the', 'party']
>>> ref1a = ['It', 'is', 'a', 'guide', 'to', 'action', 'that',
...          'ensures', 'that', 'the', 'military', 'will', 'forever',
...          'heed', 'Party', 'commands']
>>> ref1b = ['It', 'is', 'the', 'guiding', 'principle', 'which',
...          'guarantees', 'the', 'military', 'forces', 'always',
...          'being', 'under', 'the', 'command', 'of', 'the', 'Party']
>>> ref1c = ['It', 'is', 'the', 'practical', 'guide', 'for', 'the',
...          'army', 'always', 'to', 'heed', 'the', 'directions',
...          'of', 'the', 'party']
>>> hyp2 = ['he', 'read', 'the', 'book', 'because', 'he', 'was',
...         'interested', 'in', 'world', 'history']
>>> ref2a = ['he', 'was', 'interested', 'in', 'world', 'history',
...          'because', 'he', 'read', 'the', 'book']
>>> list_of_references = [[ref1a, ref1b, ref1c], [ref2a]]
>>> hypotheses = [hyp1, hyp2]
>>> corpus_bleu(list_of_references, hypotheses) 
0.5920...

The example below show that corpus_bleu() is different from averaging sentence_bleu() for hypotheses

>>> score1 = sentence_bleu([ref1a, ref1b, ref1c], hyp1)
>>> score2 = sentence_bleu([ref2a], hyp2)
>>> (score1 + score2) / 2 
0.6223...

Custom weights may be supplied to fine-tune the BLEU score further. A tuple of float weights for unigrams, bigrams, trigrams and so on can be given. >>> weights = (0.1, 0.3, 0.5, 0.1) >>> corpus_bleu(list_of_references, hypotheses, weights=weights) # doctest: +ELLIPSIS 0.5818…

This particular weight gave extra value to trigrams. Furthermore, multiple weights can be given, resulting in multiple BLEU scores. >>> weights = [ … (0.5, 0.5), … (0.333, 0.333, 0.334), … (0.25, 0.25, 0.25, 0.25), … (0.2, 0.2, 0.2, 0.2, 0.2) … ] >>> corpus_bleu(list_of_references, hypotheses, weights=weights) # doctest: +ELLIPSIS [0.8242…, 0.7067…, 0.5920…, 0.4719…]

Parameters
  • list_of_references (list(list(list(str)))) – a corpus of lists of reference sentences, w.r.t. hypotheses

  • hypotheses (list(list(str))) – a list of hypothesis sentences

  • weights (tuple(float) / list(tuple(float))) – weights for unigrams, bigrams, trigrams and so on (one or a list of weights)

  • smoothing_function (SmoothingFunction) –

  • auto_reweigh (bool) – Option to re-normalize the weights uniformly.

Returns

The corpus-level BLEU score.

Return type

float

nltk.translate.bleu_score.modified_precision(references, hypothesis, n)[source]

Calculate modified ngram precision.

The normal precision method may lead to some wrong translations with high-precision, e.g., the translation, in which a word of reference repeats several times, has very high precision.

This function only returns the Fraction object that contains the numerator and denominator necessary to calculate the corpus-level precision. To calculate the modified precision for a single pair of hypothesis and references, cast the Fraction object into a float.

The famous “the the the … ” example shows that you can get BLEU precision by duplicating high frequency words.

>>> reference1 = 'the cat is on the mat'.split()
>>> reference2 = 'there is a cat on the mat'.split()
>>> hypothesis1 = 'the the the the the the the'.split()
>>> references = [reference1, reference2]
>>> float(modified_precision(references, hypothesis1, n=1)) 
0.2857...

In the modified n-gram precision, a reference word will be considered exhausted after a matching hypothesis word is identified, e.g.

>>> reference1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'that',
...               'ensures', 'that', 'the', 'military', 'will',
...               'forever', 'heed', 'Party', 'commands']
>>> reference2 = ['It', 'is', 'the', 'guiding', 'principle', 'which',
...               'guarantees', 'the', 'military', 'forces', 'always',
...               'being', 'under', 'the', 'command', 'of', 'the',
...               'Party']
>>> reference3 = ['It', 'is', 'the', 'practical', 'guide', 'for', 'the',
...               'army', 'always', 'to', 'heed', 'the', 'directions',
...               'of', 'the', 'party']
>>> hypothesis = 'of the'.split()
>>> references = [reference1, reference2, reference3]
>>> float(modified_precision(references, hypothesis, n=1))
1.0
>>> float(modified_precision(references, hypothesis, n=2))
1.0

An example of a normal machine translation hypothesis:

>>> hypothesis1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'which',
...               'ensures', 'that', 'the', 'military', 'always',
...               'obeys', 'the', 'commands', 'of', 'the', 'party']
>>> hypothesis2 = ['It', 'is', 'to', 'insure', 'the', 'troops',
...               'forever', 'hearing', 'the', 'activity', 'guidebook',
...               'that', 'party', 'direct']
>>> reference1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'that',
...               'ensures', 'that', 'the', 'military', 'will',
...               'forever', 'heed', 'Party', 'commands']
>>> reference2 = ['It', 'is', 'the', 'guiding', 'principle', 'which',
...               'guarantees', 'the', 'military', 'forces', 'always',
...               'being', 'under', 'the', 'command', 'of', 'the',
...               'Party']
>>> reference3 = ['It', 'is', 'the', 'practical', 'guide', 'for', 'the',
...               'army', 'always', 'to', 'heed', 'the', 'directions',
...               'of', 'the', 'party']
>>> references = [reference1, reference2, reference3]
>>> float(modified_precision(references, hypothesis1, n=1)) 
0.9444...
>>> float(modified_precision(references, hypothesis2, n=1)) 
0.5714...
>>> float(modified_precision(references, hypothesis1, n=2)) 
0.5882352941176471
>>> float(modified_precision(references, hypothesis2, n=2)) 
0.07692...
Parameters
  • references (list(list(str))) – A list of reference translations.

  • hypothesis (list(str)) – A hypothesis translation.

  • n (int) – The ngram order.

Returns

BLEU’s modified precision for the nth order ngram.

Return type

Fraction

nltk.translate.bleu_score.sentence_bleu(references, hypothesis, weights=(0.25, 0.25, 0.25, 0.25), smoothing_function=None, auto_reweigh=False)[source]

Calculate BLEU score (Bilingual Evaluation Understudy) from Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. “BLEU: a method for automatic evaluation of machine translation.” In Proceedings of ACL. https://www.aclweb.org/anthology/P02-1040.pdf

>>> hypothesis1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'which',
...               'ensures', 'that', 'the', 'military', 'always',
...               'obeys', 'the', 'commands', 'of', 'the', 'party']
>>> hypothesis2 = ['It', 'is', 'to', 'insure', 'the', 'troops',
...               'forever', 'hearing', 'the', 'activity', 'guidebook',
...               'that', 'party', 'direct']
>>> reference1 = ['It', 'is', 'a', 'guide', 'to', 'action', 'that',
...               'ensures', 'that', 'the', 'military', 'will', 'forever',
...               'heed', 'Party', 'commands']
>>> reference2 = ['It', 'is', 'the', 'guiding', 'principle', 'which',
...               'guarantees', 'the', 'military', 'forces', 'always',
...               'being', 'under', 'the', 'command', 'of', 'the',
...               'Party']
>>> reference3 = ['It', 'is', 'the', 'practical', 'guide', 'for', 'the',
...               'army', 'always', 'to', 'heed', 'the', 'directions',
...               'of', 'the', 'party']
>>> sentence_bleu([reference1, reference2, reference3], hypothesis1) 
0.5045...

If there is no ngrams overlap for any order of n-grams, BLEU returns the value 0. This is because the precision for the order of n-grams without overlap is 0, and the geometric mean in the final BLEU score computation multiplies the 0 with the precision of other n-grams. This results in 0 (independently of the precision of the other n-gram orders). The following example has zero 3-gram and 4-gram overlaps:

>>> round(sentence_bleu([reference1, reference2, reference3], hypothesis2),4) 
0.0

To avoid this harsh behaviour when no ngram overlaps are found a smoothing function can be used.

>>> chencherry = SmoothingFunction()
>>> sentence_bleu([reference1, reference2, reference3], hypothesis2,
...     smoothing_function=chencherry.method1) 
0.0370...

The default BLEU calculates a score for up to 4-grams using uniform weights (this is called BLEU-4). To evaluate your translations with higher/lower order ngrams, use customized weights. E.g. when accounting for up to 5-grams with uniform weights (this is called BLEU-5) use:

>>> weights = (1./5., 1./5., 1./5., 1./5., 1./5.)
>>> sentence_bleu([reference1, reference2, reference3], hypothesis1, weights) 
0.3920...

Multiple BLEU scores can be computed at once, by supplying a list of weights. E.g. for computing BLEU-2, BLEU-3 and BLEU-4 in one computation, use: >>> weights = [ … (1./2., 1./2.), … (1./3., 1./3., 1./3.), … (1./4., 1./4., 1./4., 1./4.) … ] >>> sentence_bleu([reference1, reference2, reference3], hypothesis1, weights) # doctest: +ELLIPSIS [0.7453…, 0.6240…, 0.5045…]

Parameters
  • references (list(list(str))) – reference sentences

  • hypothesis (list(str)) – a hypothesis sentence

  • weights (tuple(float) / list(tuple(float))) – weights for unigrams, bigrams, trigrams and so on (one or a list of weights)

  • smoothing_function (SmoothingFunction) –

  • auto_reweigh (bool) – Option to re-normalize the weights uniformly.

Returns

The sentence-level BLEU score. Returns a list if multiple weights were supplied.

Return type

float / list(float)