File size: 3,382 Bytes
ced0e09 6a4fac9 ced0e09 6a4fac9 ced0e09 6a4fac9 ced0e09 6a4fac9 6be1f2a 6a4fac9 6be1f2a ced0e09 6a4fac9 ced0e09 29d0f05 6be1f2a 6a4fac9 ced0e09 6a4fac9 ced0e09 6a4fac9 ced0e09 6a4fac9 6be1f2a 6a4fac9 6be1f2a 6a4fac9 ced0e09 6a4fac9 6be1f2a |
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 |
# Copyright 2022 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.
"""ANLS - Average Normalized Levenshtein Similarity"""
import datasets
import evaluate
from compute_score import compute_score
_CITATION = """\
@article{,
title = {Binary codes capable of correcting deletions, insertions, and reversals},
journal = {Soviet physics doklady},
volume = {10},
number = {8},
pages = {707--710},
year = {1966},
url = {https://nymity.ch/sybilhunting/pdf/Levenshtein1966a.pdf},
author = {V. I. Levenshtein},
}
"""
_DESCRIPTION = """\
ANLS refer to the average normalized Levenshtein similarity.
"""
_KWARGS_DESCRIPTION = """
Computes Average Normalized Levenshtein Similarity (ANLS).
Args:
predictions: List of question-answers dictionaries with the following key-values:
- 'question_id': id of the question-answer pair as given in the references (see below)
- 'prediction_text': the text of the answer
references: List of question-answers dictionaries with the following key-values:
- 'question_id': id of the question-answer pair (see above),
- 'answers': list of possible texts for the answer, as a list of strings
Returns:
'anls': The ANLS score of predicted tokens versus the gold answer
Examples:
>>> predictions = [{'prediction_text': 'Denver Broncos', 'question_id': '56e10a3be3433e1400422b22'}]
>>> references = [{'answers': ['Denver Broncos', 'Denver R. Broncos'], 'question_id': '56e10a3be3433e1400422b22'}]
>>> anls_metric = evaluate.load("anls")
>>> results = anls_metric.compute(predictions=predictions, references=references)
>>> print(results)
{'anls_score': 100.0}
"""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class Anls(evaluate.Metric):
def _info(self):
return evaluate.MetricInfo(
description=_DESCRIPTION,
citation=_CITATION,
inputs_description=_KWARGS_DESCRIPTION,
features=datasets.Features(
{
"predictions": {"question_id": datasets.Value("string"),
"prediction_text": datasets.Value("string")},
"references": {
"question_id": datasets.Value("string"),
"answers": datasets.features.Sequence(datasets.Value("string")),
},
}
)
)
def _compute(self, predictions, references):
ground_truths = {x['question_id']: x['answers'] for x in references}
predictions = {x['question_id']: x['prediction_text'] for x in predictions}
anls_score = compute_score(predictions=predictions, ground_truths=ground_truths)
return {"anls_score": anls_score}
|