Spaces:
Runtime error
Runtime error
File size: 2,627 Bytes
46bcca0 |
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 |
import sacrebleu
import numpy as np
from rouge_score import rouge_scorer, scoring
def process_results(doc, results):
# (Pdb)doc.keys()
# dict_keys(['document', 'summary', 'id'])
# (Pdb++) results
# [' The Welsh Government has announced
# breakpoint()
completion = results[0]
# true_refs, false_refs = doc["correct_answers"], doc["incorrect_answers"]
# all_refs = true_refs + false_refs
document = doc["document"]
true_refs = [doc["summary"]]
all_refs = true_refs
# ROUGE-N
rouge_scores = [rouge([ref], [completion]) for ref in all_refs]
# ROUGE-1
rouge1_scores = [score["rouge1"] for score in rouge_scores]
# ROUGE-2
rouge2_scores = [score["rouge2"] for score in rouge_scores]
# ROUGE-L
rougeL_scores = [score["rougeLsum"] for score in rouge_scores]
res = {
"rouge1": rouge1_scores[0],
"rouge2": rouge2_scores[0],
"rougeL": rougeL_scores[0],
}
return res
def bleu(refs, preds):
"""
Returns `t5` style BLEU scores. See the related implementation:
https://github.com/google-research/text-to-text-transfer-transformer/blob/3d10afd51ba97ac29eb66ae701eca274488202f7/t5/evaluation/metrics.py#L41
:param refs:
A `list` of `list` of reference `str`s.
:param preds:
A `list` of predicted `str`s.
"""
score = sacrebleu.corpus_bleu(
preds,
refs,
smooth_method="exp",
smooth_value=0.0,
force=False,
lowercase=False,
tokenize="intl",
use_effective_order=False,
).score
return score
def rouge(refs, preds):
"""
Returns `t5` style ROUGE scores. See the related implementation:
https://github.com/google-research/text-to-text-transfer-transformer/blob/3d10afd51ba97ac29eb66ae701eca274488202f7/t5/evaluation/metrics.py#L68
:param refs:
A `list` of reference `strs`.
:param preds:
A `list` of predicted `strs`.
"""
rouge_types = ["rouge1", "rouge2", "rougeLsum"]
scorer = rouge_scorer.RougeScorer(rouge_types)
# Add newlines between sentences to correctly compute `rougeLsum`.
def _prepare_summary(summary):
summary = summary.replace(" . ", ".\n")
return summary
# Accumulate confidence intervals.
aggregator = scoring.BootstrapAggregator()
for ref, pred in zip(refs, preds):
ref = _prepare_summary(ref)
pred = _prepare_summary(pred)
aggregator.add_scores(scorer.score(ref, pred))
result = aggregator.aggregate()
return {type: result[type].mid.fmeasure * 100 for type in rouge_types}
|