Spaces:
Runtime error
Runtime error
File size: 4,384 Bytes
889e704 b0eb96e 889e704 b0eb96e 889e704 b0eb96e 889e704 b0eb96e 889e704 b0eb96e 9af909b 889e704 b0eb96e 889e704 fd7fd41 889e704 b0eb96e 889e704 b0eb96e 889e704 c7a0416 999d570 6496905 889e704 9af909b 889e704 e09d677 950dce9 7ac6c22 e09d677 889e704 de3957d 889e704 |
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 |
# 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{deng2021compression,
title={Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation},
author={Deng, Mingkai and Tan, Bowen and Liu, Zhengzhong and Xing, Eric and Hu, Zhiting},
booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
pages={7580--7605},
year={2021}
}
"""
# TODO: Add description of the module here
_DESCRIPTION = """\
This repo contains code of an automatic evaluation metric described in the paper
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
"""
# 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 texts (Hypothesis) to score. The list now only supports one piece of text
references: List of texts (Premise) to score. The list now only supports one piece of text
Returns:
ctc_score: The CTC score
Examples:
>>> ctc_score = evaluate.load("yzha/ctc_eval")
>>> results = ctc_score.compute(references=['hello world'], predictions=['hi world'])
>>> print(results)
{'ctc_score': 0.5211202502250671}
"""
# 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 CTC_Eval(evaluate.EvaluationModule):
"""TODO: Short description of my evaluation module."""
def _info(self):
# TODO: Specifies the evaluate.EvaluationModuleInfo object
return evaluate.EvaluationModuleInfo(
# 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('large_string'),
'references': datasets.Value('large_string'),
}),
# Homepage of the module for documentation
homepage="https://github.com/tanyuqian/ctc-gen-eval",
# Additional links to the codebase or references
codebase_urls=["https://github.com/tanyuqian/ctc-gen-eval"],
reference_urls=["https://github.com/tanyuqian/ctc-gen-eval"]
)
def _download_and_prepare(self, dl_manager):
"""Optional: download external resources useful to compute the scores"""
# TODO: Download external resources if needed
import nltk
nltk.download('stopwords')
import subprocess
import sys
def install(package):
subprocess.check_call([sys.executable, "-m", "pip", "install", package])
install('ctc-score')
from ctc_score import StyleTransferScorer, SummarizationScorer, DialogScorer
self.scorer = SummarizationScorer(align='D-cnndm')
self.compute(references=['hello world'], predictions=['hi world'])
def _compute(self, predictions, references):
"""Returns the scores"""
# TODO: Compute the different scores of the module
assert len(predictions) == len(references)
print('computing...')
print(predictions)
print(references)
ctc_score = self.scorer.score(doc=references[0], refs=[], hypo=predictions[0], aspect='consistency')
return {
"ctc_score": [ctc_score]
} |