File size: 5,630 Bytes
2b55a7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2020 The HuggingFace Evaluate Authors.
#
# 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.
""" ROUGE metric from Google Research github repo. """

# The dependencies in https://github.com/google-research/google-research/blob/master/rouge/requirements.txt
import absl  # Here to have a nice missing dependency error message early on
import datasets
import nltk  # Here to have a nice missing dependency error message early on
import numpy  # Here to have a nice missing dependency error message early on
import six  # Here to have a nice missing dependency error message early on
from rouge_score import rouge_scorer, scoring

import evaluate


_CITATION = """\
@inproceedings{lin-2004-rouge,
    title = "{ROUGE}: A Package for Automatic Evaluation of Summaries",
    author = "Lin, Chin-Yew",
    booktitle = "Text Summarization Branches Out",
    month = jul,
    year = "2004",
    address = "Barcelona, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W04-1013",
    pages = "74--81",
}
"""

_DESCRIPTION = """\
ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics and a software package used for
evaluating automatic summarization and machine translation software in natural language processing.
The metrics compare an automatically produced summary or translation against a reference or a set of references (human-produced) summary or translation.

Note that ROUGE is case insensitive, meaning that upper case letters are treated the same way as lower case letters.

This metrics is a wrapper around Google Research reimplementation of ROUGE:
https://github.com/google-research/google-research/tree/master/rouge
"""

_KWARGS_DESCRIPTION = """
Calculates average rouge scores for a list of hypotheses and references
Args:
    predictions: list of predictions to score. Each prediction
        should be a string with tokens separated by spaces.
    references: list of reference for each prediction. Each
        reference should be a string with tokens separated by spaces.
    rouge_types: A list of rouge types to calculate.
        Valid names:
        `"rouge{n}"` (e.g. `"rouge1"`, `"rouge2"`) where: {n} is the n-gram based scoring,
        `"rougeL"`: Longest common subsequence based scoring.
        `"rougeLSum"`: rougeLsum splits text using `"\n"`.
        See details in https://github.com/huggingface/datasets/issues/617
    use_stemmer: Bool indicating whether Porter stemmer should be used to strip word suffixes.
    use_aggregator: Return aggregates if this is set to True
Returns:
    rouge1: rouge_1 (precision, recall, f1),
    rouge2: rouge_2 (precision, recall, f1),
    rougeL: rouge_l (precision, recall, f1),
    rougeLsum: rouge_lsum (precision, recall, f1)
Examples:

    >>> rouge = evaluate.load('rouge')
    >>> predictions = ["hello there", "general kenobi"]
    >>> references = ["hello there", "general kenobi"]
    >>> results = rouge.compute(predictions=predictions, references=references)
    >>> print(list(results.keys()))
    ['rouge1', 'rouge2', 'rougeL', 'rougeLsum']
    >>> print(results["rouge1"])
    AggregateScore(low=Score(precision=1.0, recall=1.0, fmeasure=1.0), mid=Score(precision=1.0, recall=1.0, fmeasure=1.0), high=Score(precision=1.0, recall=1.0, fmeasure=1.0))
    >>> print(results["rouge1"].mid.fmeasure)
    1.0
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class Rouge(evaluate.EvaluationModule):
    def _info(self):
        return evaluate.EvaluationModuleInfo(
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            features=datasets.Features(
                {
                    "predictions": datasets.Value("string", id="sequence"),
                    "references": datasets.Value("string", id="sequence"),
                }
            ),
            codebase_urls=["https://github.com/google-research/google-research/tree/master/rouge"],
            reference_urls=[
                "https://en.wikipedia.org/wiki/ROUGE_(metric)",
                "https://github.com/google-research/google-research/tree/master/rouge",
            ],
        )

    def _compute(self, predictions, references, rouge_types=None, use_aggregator=True, use_stemmer=False):
        if rouge_types is None:
            rouge_types = ["rouge1", "rouge2", "rougeL", "rougeLsum"]

        scorer = rouge_scorer.RougeScorer(rouge_types=rouge_types, use_stemmer=use_stemmer)
        if use_aggregator:
            aggregator = scoring.BootstrapAggregator()
        else:
            scores = []

        for ref, pred in zip(references, predictions):
            score = scorer.score(ref, pred)
            if use_aggregator:
                aggregator.add_scores(score)
            else:
                scores.append(score)

        if use_aggregator:
            result = aggregator.aggregate()
        else:
            result = {}
            for key in scores[0]:
                result[key] = list(score[key] for score in scores)

        return result