Extended Edit Distance¶
Module Interface¶
- class torchmetrics.ExtendedEditDistance(language='en', return_sentence_level_score=False, alpha=2.0, rho=0.3, deletion=0.2, insertion=1.0, compute_on_step=None, **kwargs)[source]
Computes extended edit distance score (ExtendedEditDistance) [1] for strings or list of strings.
The metric utilises the Levenshtein distance and extends it by adding a jump operation.
- Parameters
language¶ (
Literal
[‘en’, ‘ja’]) – Language used in sentences. Only supports English (en) and Japanese (ja) for now.return_sentence_level_score¶ (
bool
) – An indication of whether sentence-level EED score is to be returnedalpha¶ (
float
) – optimal jump penalty, penalty for jumps between charactersrho¶ (
float
) – coverage cost, penalty for repetition of charactersinsertion¶ (
float
) – penalty for insertion or substitution of charactercompute_on_step¶ (
Optional
[bool
]) –Forward only calls
update()
and returns None if this is set to False.Deprecated since version v0.8: Argument has no use anymore and will be removed v0.9.
kwargs¶ (
Dict
[str
,Any
]) – Additional keyword arguments, see Advanced metric settings for more info.
- Returns
Extended edit distance score as a tensor
Example
>>> from torchmetrics import ExtendedEditDistance >>> preds = ["this is the prediction", "here is an other sample"] >>> target = ["this is the reference", "here is another one"] >>> metric = ExtendedEditDistance() >>> metric(preds=preds, target=target) tensor(0.3078)
References
[1] P. Stanchev, W. Wang, and H. Ney, “EED: Extended Edit Distance Measure for Machine Translation”, submitted to WMT 2019. ExtendedEditDistance
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- compute()[source]
Calculate extended edit distance score.
Functional Interface¶
- torchmetrics.functional.extended_edit_distance(preds, target, language='en', return_sentence_level_score=False, alpha=2.0, rho=0.3, deletion=0.2, insertion=1.0)[source]
Computes extended edit distance score (ExtendedEditDistance) [1] for strings or list of strings. The metric utilises the Levenshtein distance and extends it by adding a jump operation.
- Parameters
preds¶ (
Union
[str
,Sequence
[str
]]) – An iterable of hypothesis corpus.target¶ (
Sequence
[Union
[str
,Sequence
[str
]]]) – An iterable of iterables of reference corpus.language¶ (
Literal
[‘en’, ‘ja’]) – Language used in sentences. Only supports English (en) and Japanese (ja) for now. Defaults to enreturn_sentence_level_score¶ (
bool
) – An indication of whether sentence-level EED score is to be returned.alpha¶ (
float
) – optimal jump penalty, penalty for jumps between charactersrho¶ (
float
) – coverage cost, penalty for repetition of charactersinsertion¶ (
float
) – penalty for insertion or substitution of character
- Return type
- Returns
Extended edit distance score as a tensor
Example
>>> from torchmetrics.functional import extended_edit_distance >>> preds = ["this is the prediction", "here is an other sample"] >>> target = ["this is the reference", "here is another one"] >>> extended_edit_distance(preds=preds, target=target) tensor(0.3078)
References
[1] P. Stanchev, W. Wang, and H. Ney, “EED: Extended Edit Distance Measure for Machine Translation”, submitted to WMT 2019. ExtendedEditDistance