Add optional use_effective_order parameter to BLEU score (#1862)

The original BLEU score fails for answers shorter than four tokens
because the number of 4-grams is zero. Adding the use_effective_order
parameter allows users to obtain scores by considering only n-grams up
to the number of tokens in the answer when ( N < 4 ). This feature is
already implemented in sacreBLEU, so we only need to add the parameter
to the BLEU object in ragas. The default is set to False to maintain
previous behavior.

---------

Co-authored-by: Shahules786 <[email protected]>

Author: JonasElburgUVA

src/ragas/metrics/_bleu_score.py

@@ -15,6 +15,7 @@ class BleuScore(SingleTurnMetric):
         default_factory=lambda: {MetricType.SINGLE_TURN: {"reference", "response"}}
     )
     language: str = "english"
+    kwargs: t.Dict[str, t.Any] = field(default_factory=dict)
 
     def __post_init__(self):
         try:
@@ -41,7 +42,7 @@ async def _single_turn_ascore(
 
         reference = [[reference] for reference in reference_sentences]
         response = response_sentences
-        score = self.corpus_bleu(response, reference).score / 100
+        score = self.corpus_bleu(response, reference, **self.kwargs).score / 100
         assert isinstance(score, float), "Expecting a float"
         return score