textgen_evaluator.py

import datasets
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)
"""


@datasets.utils.file_utils.add_start_docstrings(
    _DESCRIPTION, _KWARGS_DESCRIPTION
)
class TextGenEvaluatorTest(datasets.Metric):
    def _info(self):
        return datasets.MetricInfo(
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            features=datasets.Features(
                {
                    "predictions": datasets.Value("string"),
                    "references": datasets.Value("string"),
                }
            ),
            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_score = evaluate.load("rouge")

        scores = rouge_score.compute(
            predictions=predictions, references=references
        )
        bleu_score = evaluate.load("bleu")
        results = bleu_score.compute(
            predictions=predictions, references=references
        )

        return {"ROUGE": scores, "BLEU": results}