add bleu 1 2 3 4 compute

README.md

@@ -1,7 +1,7 @@
 ---
 title: bleu_1234
-datasets:
--  
+datasets: 
+- "none"
 tags:
 - evaluate
 - metric

bleu_1234.py

@@ -70,10 +70,20 @@ class bleu_1234(evaluate.Metric):
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
+            features=[
+                datasets.Features(
+                    {
+                        "predictions": datasets.Value("string", id="sequence"),
+                        "references": datasets.Sequence(datasets.Value("string", id="sequence"), id="references"),
+                    }
+                ),
+                datasets.Features(
+                    {
+                        "predictions": datasets.Value("string", id="sequence"),
+                        "references": datasets.Value("string", id="sequence"),
+                    }
+                ),
+            ],
             # Homepage of the module for documentation
             homepage="http://module.homepage",
             # Additional links to the codebase or references
@@ -84,12 +94,25 @@ class bleu_1234(evaluate.Metric):
     def _download_and_prepare(self, dl_manager):
         """Optional: download external resources useful to compute the scores"""
         # TODO: Download external resources if needed
-        pass
+        import torch
+        from torchmetrics.text import BLEUScore
 
     def _compute(self, predictions, references):
         """Returns the scores"""
         # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
-        return {
-            "accuracy": accuracy,
-        }
+        if isinstance(references[0], str):
+            references = [[ref] for ref in references]
+
+        bleu = BLEUScore()
+        bleu1 = bleu(preds, target, n_gram=1)
+        bleu2 = bleu(preds, target, n_gram=2)
+        bleu3 = bleu(preds, target, n_gram=3)
+        bleu4 = bleu(preds, target, n_gram=4)
+
+        output_dict = {
+            "bleu-1": bleu1,
+            "bleu-2": bleu2,
+            "bleu-3": bleu3,
+            "bleu-4": bleu4,
+        }
+        return output_dict