File size: 6,102 Bytes
9c6594c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 |
# Copyright The Lightning team.
#
# 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.
# referenced from
# Library Name: torchtext
# Authors: torchtext authors and @sluks
# Date: 2020-07-18
# Link: https://pytorch.org/text/_modules/torchtext/data/metrics.html#bleu_score
from collections.abc import Sequence
from typing import Any, Optional, Union
from torch import Tensor
from torchmetrics.functional.text.bleu import _bleu_score_update
from torchmetrics.functional.text.sacre_bleu import _SacreBLEUTokenizer, _TokenizersLiteral
from torchmetrics.text.bleu import BLEUScore
from torchmetrics.utilities.imports import _MATPLOTLIB_AVAILABLE
from torchmetrics.utilities.plot import _AX_TYPE, _PLOT_OUT_TYPE
if not _MATPLOTLIB_AVAILABLE:
__doctest_skip__ = ["SacreBLEUScore.plot"]
class SacreBLEUScore(BLEUScore):
"""Calculate `BLEU score`_ of machine translated text with one or more references.
This implementation follows the behaviour of `SacreBLEU`_. The SacreBLEU implementation differs from the NLTK BLEU
implementation in tokenization techniques.
As input to ``forward`` and ``update`` the metric accepts the following input:
- ``preds`` (:class:`~Sequence`): An iterable of machine translated corpus
- ``target`` (:class:`~Sequence`): An iterable of iterables of reference corpus
As output of ``forward`` and ``compute`` the metric returns the following output:
- ``sacre_bleu`` (:class:`~torch.Tensor`): A tensor with the SacreBLEU Score
Args:
n_gram: Gram value ranged from 1 to 4
smooth: Whether to apply smoothing, see `SacreBLEU`_
tokenize: Tokenization technique to be used. Choose between ``'none'``, ``'13a'``, ``'zh'``, ``'intl'``,
``'char'``, ``'ja-mecab'``, ``'ko-mecab'``, ``'flores101'`` and ``'flores200'``.
lowercase: If ``True``, BLEU score over lowercased text is calculated.
kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
weights:
Weights used for unigrams, bigrams, etc. to calculate BLEU score.
If not provided, uniform weights are used.
Raises:
ValueError:
If ``tokenize`` not one of 'none', '13a', 'zh', 'intl' or 'char'
ValueError:
If ``tokenize`` is set to 'intl' and `regex` is not installed
ValueError:
If a length of a list of weights is not ``None`` and not equal to ``n_gram``.
Example:
>>> from torchmetrics.text import SacreBLEUScore
>>> preds = ['the cat is on the mat']
>>> target = [['there is a cat on the mat', 'a cat is on the mat']]
>>> sacre_bleu = SacreBLEUScore()
>>> sacre_bleu(preds, target)
tensor(0.7598)
Additional References:
- Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence
and Skip-Bigram Statistics by Chin-Yew Lin and Franz Josef Och `Machine Translation Evolution`_
"""
is_differentiable: bool = False
higher_is_better: bool = True
full_state_update: bool = True
plot_lower_bound: float = 0.0
plot_upper_bound: float = 1.0
def __init__(
self,
n_gram: int = 4,
smooth: bool = False,
tokenize: _TokenizersLiteral = "13a",
lowercase: bool = False,
weights: Optional[Sequence[float]] = None,
**kwargs: Any,
) -> None:
super().__init__(n_gram=n_gram, smooth=smooth, weights=weights, **kwargs)
self.tokenizer = _SacreBLEUTokenizer(tokenize, lowercase)
def update(self, preds: Sequence[str], target: Sequence[Sequence[str]]) -> None:
"""Update state with predictions and targets."""
self.preds_len, self.target_len = _bleu_score_update(
preds,
target,
self.numerator,
self.denominator,
self.preds_len,
self.target_len,
self.n_gram,
self.tokenizer,
)
def plot(
self, val: Optional[Union[Tensor, Sequence[Tensor]]] = None, ax: Optional[_AX_TYPE] = None
) -> _PLOT_OUT_TYPE:
"""Plot a single or multiple values from the metric.
Args:
val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
If no value is provided, will automatically call `metric.compute` and plot that result.
ax: An matplotlib axis object. If provided will add plot to that axis
Returns:
Figure and Axes object
Raises:
ModuleNotFoundError:
If `matplotlib` is not installed
.. plot::
:scale: 75
>>> # Example plotting a single value
>>> from torchmetrics.text import SacreBLEUScore
>>> metric = SacreBLEUScore()
>>> preds = ['the cat is on the mat']
>>> target = [['there is a cat on the mat', 'a cat is on the mat']]
>>> metric.update(preds, target)
>>> fig_, ax_ = metric.plot()
.. plot::
:scale: 75
>>> # Example plotting multiple values
>>> from torchmetrics.text import SacreBLEUScore
>>> metric = SacreBLEUScore()
>>> preds = ['the cat is on the mat']
>>> target = [['there is a cat on the mat', 'a cat is on the mat']]
>>> values = [ ]
>>> for _ in range(10):
... values.append(metric(preds, target))
>>> fig_, ax_ = metric.plot(values)
"""
return self._plot(val, ax)
|