imddlmZddlmZmZmZmZddlZddlmZm Z ddl m Z m Z m Z ddlmZddlmZddlmZmZesd gZGd d eZy) )Sequence)AnyListOptionalUnionN)Tensortensor) _ter_compute _ter_update_TercomTokenizer)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzTranslationEditRate.plotcPeZdZUdZdZeed<dZeed<dZeed<dZ e ed<dZ e ed <e ed <e ed <d Z eee ed < ddededededededd ffd Zdeeeefdeeeeefdd fdZdee ee e fffdZ ddeee ee fdeedefdZxZS)TranslationEditRateauCalculate Translation edit rate (`TER`_) of machine translated text with one or more references. This implementation follows the one from `SacreBleu_ter`_, which is a near-exact reimplementation of the Tercom algorithm, produces identical results on all "sane" outputs. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~Sequence`): An iterable of hypothesis corpus - ``target`` (:class:`~Sequence`): An iterable of iterables of reference corpus As output of ``forward`` and ``compute`` the metric returns the following output: - ``ter`` (:class:`~torch.Tensor`): if ``return_sentence_level_score=True`` return a corpus-level translation edit rate with a list of sentence-level translation_edit_rate, else return a corpus-level translation edit rate Args: normalize: An indication whether a general tokenization to be applied. no_punctuation: An indication whteher a punctuation to be removed from the sentences. lowercase: An indication whether to enable case-insensitivity. asian_support: An indication whether asian characters to be processed. return_sentence_level_score: An indication whether a sentence-level TER to be returned. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torchmetrics.text import TranslationEditRate >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> ter = TranslationEditRate() >>> ter(preds, target) tensor(0.1538) Fis_differentiablehigher_is_betterfull_state_updateplot_lower_boundg?plot_upper_boundtotal_num_edits total_tgt_lenN sentence_ter normalizeno_punctuation lowercase asian_supportreturn_sentence_level_scorekwargsreturnc t|d i|t|tst d|dt|tst d|dt|tst d|dt|tst d|dt |||||_||_|jdtdd |jd tdd |jr|jd gd yy)Nz2eN D ,predstargetct|||j|j|j|j\|_|_|_y)z*Update state with predictions and targets.N)r r.rrr)r0r4r5s r2updatezTranslationEditRate.updateesEFQ   NN        G Cd0$2Cr3ct|j|j}|j!|t j |jfS|S)z)Calculate the translate error rate (TER).)r rrrtorchr')r0ters r2computezTranslationEditRate.computepsE4//1C1CD    ( $"3"344 4 r3valaxc&|j||S)aPlot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> from torchmetrics.text import TranslationEditRate >>> metric = TranslationEditRate() >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> from torchmetrics.text import TranslationEditRate >>> metric = TranslationEditRate() >>> preds = ['the cat is on the mat'] >>> target = [['there is a cat on the mat', 'a cat is on the mat']] >>> values = [ ] >>> for _ in range(10): ... values.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(values) )_plot)r0r<r=s r2plotzTranslationEditRate.plotwsTzz#r""r3)FFTFF)NN)__name__ __module__ __qualname____doc__rr,__annotations__rrrfloatrrrrrrr*rstrrr7tupler;rrr@ __classcell__)r1s@r2rrs_B$t#"d"#t#!e!!e!+/L(4<(/ $#,1 EEE E  E &* EE E6  E#x}"45  xcS[\_S`N`Ha?b  gk  vuVV^'<<=_c*#E&(6*:":;<*#IQRZI[*# *#r3r)collections.abcrtypingrrrrr9rr torchmetrics.functional.text.terr r r torchmetrics.metricr torchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rr(r3r2rQs?%-- XX&@@23C#&C#r3