File size: 6,133 Bytes
b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b a8d5201 b9ddd6b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
# 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.
"""SemScore metric"""
import evaluate
import datasets
import torch
from transformers import AutoTokenizer, AutoModel
from tqdm import tqdm
_CITATION = """\
@misc{semscore,
title={SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity},
author={Ansar Aynetdinov and Alan Akbik},
year={2024},
eprint={2401.17072},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2401.17072},
}
"""
_DESCRIPTION = """\
SemScore measures semantic textual similarity between candidate and reference texts. It has been shown to
strongly correlate with human judgment on a system-level when evaluating instruction-tuned models.
"""
_KWARGS_DESCRIPTION = """
Calculates how good are predictions given some references, using certain scores
Args:
predictions (list of str): list of predictions (instruction completions) to score. Each prediction
should be a string.
references (list of str): list of references (target completions). Each reference should be a string.
batch_size (int): the batch size for predictions.
device (str): CPU/GPU device.
Returns:
semscore: aggregated system-level SemScore,
similarities: cosine similarities between individual prediction-reference pairs,
Examples:
>>> predictions = ['This is an example sentence', 'Each sentence is considered']
>>> references = ['This is an example sentence', 'Each sentence is considered']
>>> semscore = evaluate.load("semscore")
>>> results = semscore.compute(predictions=predictions, references=references)
>>> print(results['semscore'])
100.0
"""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class SemScore(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"""
if self.config_name is None:
checkpoint = "sentence-transformers/all-mpnet-base-v2"
else:
checkpoint = self.config_name
# Load model and tokenizer from HuggingFace Hub
self.model = AutoModel.from_pretrained(checkpoint)
self.model.eval()
self.tokenizer = AutoTokenizer.from_pretrained(checkpoint)
def mean_pooling(model_output, attention_mask):
"""Mean pooling over all tokens - take attention mask into account for correct averaging"""
token_embeddings = model_output[0]
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
def _compute(
self,
predictions,
references,
batch_size=32,
device=None,
):
"""Returns the scores"""
assert len(predictions) == len(references), "predictions and references should have the same length."
if device is not None:
if "cuda" in device:
assert torch.cuda.is_available()
self.model.to(device)
else:
device = "cpu"
pooled_refs, pooled_preds = [], []
with torch.inference_mode():
for i in tqdm(range(0, len(references), batch_size), desc="Processing batches"):
batch_refs = references[i : i + batch_size]
batch_preds = predictions[i : i + batch_size]
encoded_refs = self.tokenizer(batch_refs, padding=True, truncation=True, return_tensors='pt')
encoded_preds = self.tokenizer(batch_preds, padding=True, truncation=True, return_tensors='pt')
model_output_refs = self.model(**encoded_refs.to(device))
model_output_preds = self.model(**encoded_predictions.to(device))
batch_pooled_refs = mean_pooling(model_output_refs, encoded_refs['attention_mask'])
batch_pooled_preds = mean_pooling(model_output_preds, encoded_preds['attention_mask'])
pooled_refs.append(batch_pooled_refs)
pooled_preds.append(batch_pooled_preds)
pooled_refs, pooled_preds = torch.cat(pooled_refs), torch.cat(pooled_preds)
similarities = torch.nn.functional.F.cosine_similarity(pooled_refs, pooled_preds)
similarities = similarities * 100
semscore = torch.mean(similarities)
return {
"semscore": round(semscore.item(), 2),
"similarities": similarities.tolist()
} |