File size: 5,560 Bytes
766a079 50bd00a 766a079 50bd00a 766a079 |
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 |
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# 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.
"""TODO: Add a description here."""
import evaluate
import datasets
# TODO: Add BibTeX citation
_CITATION = """\
@inproceedings{lemesle-etal-2025-paraphrase,
title = "Paraphrase Generation Evaluation Powered by an {LLM}: A Semantic Metric, Not a Lexical One",
author = "Lemesle, Quentin and
Chevelu, Jonathan and
Martin, Philippe and
Lolive, Damien and
Delhay, Arnaud and
Barbot, Nelly",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.538/",
pages = "8057--8087",
abstract = "Evaluating automatic paraphrase production systems is a difficult task as it involves, among other things, assessing the semantic proximity between two sentences. Usual measures are based on lexical distances, or at least on semantic embedding alignments. The rise of Large Language Models (LLM) has provided tools to model relationships within a text thanks to the attention mechanism. In this article, we introduce ParaPLUIE, a new measure based on a log likelihood ratio from an LLM, to assess the quality of a potential paraphrase. This measure is compared with usual measures on two known by the NLP community datasets prior to this study. Three new small datasets have been built to allow metrics to be compared in different scenario and to avoid data contamination bias. According to evaluations, the proposed measure is better for sorting pairs of sentences by semantic proximity. In particular, it is much more independent to lexical distance and provides an interpretable classification threshold between paraphrases and non-paraphrases."
}
"""
# TODO: Add description of the module here
_DESCRIPTION = """\
ParaPLUIE is a metric for evaluating the semantic proximity of two sentences.
ParaPLUIE use the perplexity of an LLM to compute a confidence score.
It has shown the highest correlation with human judgement on paraphrase classification meanwhile reamin the computional cost low as it roughtly equal to one token generation cost.
"""
# TODO: Add description of the arguments of the module here
_KWARGS_DESCRIPTION = """
Calculates how good are predictions given some references, using certain scores
Args:
predictions: list of predictions to score. Each predictions
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.
Returns:
accuracy: description of the first score,
another_score: description of the second score,
Examples:
Examples should be written in doctest format, and should illustrate how
to use the function.
>>> my_new_module = evaluate.load("my_new_module")
>>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
>>> print(results)
{'accuracy': 1.0}
"""
# TODO: Define external resources urls if needed
BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class ParaPLUIE(evaluate.Metric):
"""TODO: Short description of my evaluation module."""
def _info(self):
# TODO: Specifies the evaluate.EvaluationModuleInfo object
return evaluate.MetricInfo(
# This is the description that will appear on the modules page.
module_type="metric",
description=_DESCRIPTION,
citation=_CITATION,
inputs_description=_KWARGS_DESCRIPTION,
# This defines the format of each prediction and reference
features=datasets.Features({
'predictions': datasets.Value('int64'),
'references': datasets.Value('int64'),
}),
# Homepage of the module for documentation
homepage="http://module.homepage",
# Additional links to the codebase or references
codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
reference_urls=["http://path.to.reference.url/new_module"]
)
def _download_and_prepare(self, dl_manager):
"""Optional: download external resources useful to compute the scores"""
# TODO: Download external resources if needed
pass
def _compute(self, predictions, references):
"""Returns the scores"""
# TODO: Compute the different scores of the module
accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
return {
"accuracy": accuracy,
} |