evaluate/metrics/bleu/bleu.py

# 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.
""" BLEU metric. """

import datasets

import evaluate

from .nmt_bleu import compute_bleu  # From: https://github.com/tensorflow/nmt/blob/master/nmt/scripts/bleu.py
from .tokenizer_13a import Tokenizer13a


_CITATION = """\
@INPROCEEDINGS{Papineni02bleu:a,
    author = {Kishore Papineni and Salim Roukos and Todd Ward and Wei-jing Zhu},
    title = {BLEU: a Method for Automatic Evaluation of Machine Translation},
    booktitle = {},
    year = {2002},
    pages = {311--318}
}
@inproceedings{lin-och-2004-orange,
    title = "{ORANGE}: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation",
    author = "Lin, Chin-Yew  and
      Och, Franz Josef",
    booktitle = "{COLING} 2004: Proceedings of the 20th International Conference on Computational Linguistics",
    month = "aug 23{--}aug 27",
    year = "2004",
    address = "Geneva, Switzerland",
    publisher = "COLING",
    url = "https://www.aclweb.org/anthology/C04-1072",
    pages = "501--507",
}
"""

_DESCRIPTION = """\
BLEU (Bilingual Evaluation Understudy) is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another.
Quality is considered to be the correspondence between a machine's output and that of a human: "the closer a machine translation is to a professional human translation, the better it is"
– this is the central idea behind BLEU. BLEU was one of the first metrics to claim a high correlation with human judgements of quality, and remains one of the most popular automated and inexpensive metrics.

Scores are calculated for individual translated segments—generally sentences—by comparing them with a set of good quality reference translations.
Those scores are then averaged over the whole corpus to reach an estimate of the translation's overall quality.
Neither intelligibility nor grammatical correctness are not taken into account.
"""

_KWARGS_DESCRIPTION = """
Computes BLEU score of translated segments against one or more references.
Args:
    predictions: list of translations to score.
    references: list of lists of or just a list of references for each translation.
    tokenizer : approach used for tokenizing `predictions` and `references`.
        The default tokenizer is `tokenizer_13a`, a minimal tokenization approach that is equivalent to `mteval-v13a`, used by WMT.
        This can be replaced by any function that takes a string as input and returns a list of tokens as output.
    max_order: Maximum n-gram order to use when computing BLEU score.
    smooth: Whether or not to apply Lin et al. 2004 smoothing.
Returns:
    'bleu': bleu score,
    'precisions': geometric mean of n-gram precisions,
    'brevity_penalty': brevity penalty,
    'length_ratio': ratio of lengths,
    'translation_length': translation_length,
    'reference_length': reference_length
Examples:

    >>> predictions = ["hello there general kenobi", "foo bar foobar"]
    >>> references = [
    ...     ["hello there general kenobi", "hello there!"],
    ...     ["foo bar foobar"]
    ... ]
    >>> bleu = evaluate.load("bleu")
    >>> results = bleu.compute(predictions=predictions, references=references)
    >>> print(results["bleu"])
    1.0
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class Bleu(evaluate.Metric):
    def _info(self):
        return evaluate.MetricInfo(
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            features=[
                datasets.Features(
                    {
                        "predictions": datasets.Value("string", id="sequence"),
                        "references": datasets.Sequence(datasets.Value("string", id="sequence"), id="references"),
                    }
                ),
                datasets.Features(
                    {
                        "predictions": datasets.Value("string", id="sequence"),
                        "references": datasets.Value("string", id="sequence"),
                    }
                ),
            ],
            codebase_urls=["https://github.com/tensorflow/nmt/blob/master/nmt/scripts/bleu.py"],
            reference_urls=[
                "https://en.wikipedia.org/wiki/BLEU",
                "https://towardsdatascience.com/evaluating-text-output-in-nlp-bleu-at-your-own-risk-e8609665a213",
            ],
        )

    def _compute(self, predictions, references, tokenizer=Tokenizer13a(), max_order=4, smooth=False):
        # if only one reference is provided make sure we still use list of lists
        if isinstance(references[0], str):
            references = [[ref] for ref in references]

        references = [[tokenizer(r) for r in ref] for ref in references]
        predictions = [tokenizer(p) for p in predictions]
        score = compute_bleu(
            reference_corpus=references, translation_corpus=predictions, max_order=max_order, smooth=smooth
        )
        (bleu, precisions, bp, ratio, translation_length, reference_length) = score
        return {
            "bleu": bleu,
            "precisions": precisions,
            "brevity_penalty": bp,
            "length_ratio": ratio,
            "translation_length": translation_length,
            "reference_length": reference_length,
        }