-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbleu.py
161 lines (136 loc) · 5.63 KB
/
bleu.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
# The following file is a modified version of https://github.com/microsoft/CodeXGLUE/blob/main/Code-Code/code-refinement/evaluator/bleu.py
# As per Apache 2.0, the license originally included with the code must be included here.
# The following modifications have been made:
# - Make _bleu deal with lists rather than files
# - Remove presumed legacy code for dealing with multiple files at a time
# - Abstracted notation of tokenization to function tokenize_line
# - Clean some spacing
# - Removed rounding from _bleu (round(100 * bleu_score,2) ---> bleu_score)
# - Passed smooth through from _bleu
# - Add lower parameter to _bleu
# - Fixed divide-by-zero errors
# Copyright 2017 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Python implementation of BLEU and smooth-BLEU.
This module provides a Python implementation of BLEU and smooth-BLEU.
Smooth BLEU is computed following the method outlined in the paper:
Chin-Yew Lin, Franz Josef Och. ORANGE: a method for evaluating automatic
evaluation metrics for machine translation. COLING 2004.
"""
import collections
import math
def _get_ngrams(segment, max_order):
"""Extracts all n-grams upto a given maximum order from an input segment.
Args:
segment: text segment from which n-grams will be extracted.
max_order: maximum length in tokens of the n-grams returned by this
methods.
Returns:
The Counter containing all n-grams upto max_order in segment
with a count of how many times each n-gram occurred.
"""
ngram_counts = collections.Counter()
for order in range(1, max_order + 1):
for i in range(0, len(segment) - order + 1):
ngram = tuple(segment[i:i+order])
ngram_counts[ngram] += 1
return ngram_counts
def compute_bleu(reference_corpus, translation_corpus, max_order=4,
smooth=False, lower=False):
"""Computes BLEU score of translated segments against one or more references.
Args:
reference_corpus: list of lists of references for each translation. Each
reference should be tokenized into a list of tokens.
translation_corpus: list of translations to score. Each translation
should be tokenized into a list of tokens.
max_order: Maximum n-gram order to use when computing BLEU score.
smooth: Whether or not to apply Lin et al. 2004 smoothing.
Returns:
3-Tuple with the BLEU score, n-gram precisions, geometric mean of n-gram
precisions and brevity penalty.
"""
matches_by_order = [0] * max_order
possible_matches_by_order = [0] * max_order
reference_length = 0
translation_length = 0
for (references, translation) in zip(reference_corpus,
translation_corpus):
reference_length += min(len(r) for r in references)
translation_length += len(translation)
merged_ref_ngram_counts = collections.Counter()
for reference in references:
merged_ref_ngram_counts |= _get_ngrams(reference, max_order)
translation_ngram_counts = _get_ngrams(translation, max_order)
overlap = translation_ngram_counts & merged_ref_ngram_counts
for ngram in overlap:
matches_by_order[len(ngram)-1] += overlap[ngram]
for order in range(1, max_order+1):
possible_matches = len(translation) - order + 1
if possible_matches > 0:
possible_matches_by_order[order-1] += possible_matches
precisions = [0] * max_order
for i in range(0, max_order):
if smooth:
precisions[i] = ((matches_by_order[i] + 1.) /
(possible_matches_by_order[i] + 1.))
else:
if possible_matches_by_order[i] > 0:
precisions[i] = (float(matches_by_order[i]) /
possible_matches_by_order[i])
else:
precisions[i] = 0.0
if min(precisions) > 0:
p_log_sum = sum((1. / max_order) * math.log(p) for p in precisions)
geo_mean = math.exp(p_log_sum)
else:
geo_mean = 0
# we assume the reference length (totoal length of references) is != 0
# in BLEU.grade([""], ["lalala"]), this would error; this is an exceedingly unlikey scenario
ratio = float(translation_length) / reference_length
if ratio > 1.0:
bp = 1.
else:
if ratio == 0:
# special case: lim x->0 e^(1-1/x) = 0, so we can avoid the divide-by-zero error
bp = 0.
else:
bp = math.exp(1 - 1. / ratio)
bleu = geo_mean * bp
return (bleu, precisions, bp, ratio, translation_length, reference_length)
def tokenize_line(line, lower=False):
if lower:
line = line.lower()
return line.strip().split()
def _bleu(reference_lines, translation_lines, subword_option=None, smooth=True, lower=False):
max_order = 4
reference_text = [
tokenize_line(line, lower=lower)
for line in reference_lines
]
per_segment_references = [
[ line ]
for line in reference_text
]
translations = [
tokenize_line(line, lower=lower)
for line in translation_lines
]
bleu_score, _, _, _, _, _ = compute_bleu(
per_segment_references,
translations,
max_order,
smooth
)
return bleu_score