o .wÖiã@sŽddlmZddlmZmZmZddlmZddlm Z ddl m Z m Z ddl mZddlmZddlmZmZes=d gZGd d „d eƒZd S) é)ÚSequence)ÚAnyÚOptionalÚUnion)ÚTensor)Ú_bleu_score_update)Ú_SacreBLEUTokenizerÚ_TokenizersLiteral)Ú BLEUScore)Ú_MATPLOTLIB_AVAILABLE)Ú_AX_TYPEÚ_PLOT_OUT_TYPEúSacreBLEUScore.plotcsàeZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <   dde dede dedeee dedd f‡fdd„ Zdeedeeedd fdd„Z d deeeeefdeedefdd„Z‡ZS)!ÚSacreBLEUScorea¤ 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 .. note:: In the original SacreBLEU, references are passed as a list of reference sets (grouped by reference index). In TorchMetrics, references are passed grouped per prediction (each prediction has its own list of references). For example:: # Predictions preds = ['The dog bit the man.', "It wasn't surprising.", 'The man had just bitten him.'] # Original SacreBLEU: refs = [ ['The dog bit the man.', 'It was not unexpected.', 'The man bit him first.'], # First set ['The dog had bit the man.', 'No one was surprised.', 'The man had bitten the dog.'], # Second set ] # TorchMetrics SacreBLEU: target = [ ['The dog bit the man.', 'The dog had bit the man.'], # References for first prediction ['It was not unexpected.', 'No one was surprised.'], # References for second prediction ['The man bit him first.', 'The man had bitten the dog.'], # References for third prediction ] 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`_ FÚis_differentiableTÚhigher_is_betterÚfull_state_updategÚplot_lower_boundgð?Úplot_upper_boundéÚ13aNÚn_gramÚsmoothÚtokenizeÚ lowercaseÚweightsÚkwargsÚreturnc s*tƒjd|||dœ|¤Žt||ƒ|_dS)N)rrr©)ÚsuperÚ__init__rÚ tokenizer)Úselfrrrrrr©Ú __class__rúY/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/text/sacre_bleu.pyr qs zSacreBLEUScore.__init__ÚpredsÚtargetc Cs.t|||j|j|j|j|j|jƒ\|_|_dS)z*Update state with predictions and targets.N)rÚ numeratorÚ denominatorÚ preds_lenÚ target_lenrr!)r"r&r'rrr%Úupdate}søzSacreBLEUScore.updateÚvalÚaxcCs | ||¡S)a 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) )Ú_plot)r"r-r.rrr%ÚplotŠs *r)rFrFN)NN)Ú__name__Ú __module__Ú __qualname__Ú__doc__rÚboolÚ__annotations__rrrÚfloatrÚintr rrrr Ústrr,rrr r r0Ú __classcell__rrr#r%r#sH  G    úþýüû úùø" ÿÿÿþrN)Úcollections.abcrÚtypingrrrÚtorchrÚ!torchmetrics.functional.text.bleurÚ'torchmetrics.functional.text.sacre_bleurr Útorchmetrics.text.bleur Útorchmetrics.utilities.importsr Útorchmetrics.utilities.plotr r Ú__doctest_skip__rrrrr%Ús