added example to README

README.md

@@ -10,3 +10,14 @@ pinned: false
 ---
 
 iBLEU measures the adequacy and dissimilarity of generated paraphrases.
+
+Example:
+```
+    >>> inputs = ["greetings general kenobi", "foo  foo bar bar"]
+    >>> predictions = ["hello there general kenobi", "foo bar foobar"]
+    >>> references = [["hello there general kenobi", "hello there !"], ["foo bar foobar", "foo bar foobar"]]
+    >>> ibleu = evaluate.load("rahular/ibleu")
+    >>> results = ibleu.compute(inputs=inputs, predictions=predictions, references=references)
+    >>> print(results)
+    {'score': 60.41585343630594}
+```

ibleu.py

@@ -52,7 +52,7 @@ Args:
     use_effective_order (`bool`): If `True`, stops including n-gram orders for which precision is 0. This should be `True`, if sentence-level BLEU will be computed. Defaults to `False`.
 Returns:
     'score': iBLEU score,
-Examples:
+Example:
     >>> inputs = ["greetings general kenobi", "foo  foo bar bar"]
     >>> predictions = ["hello there general kenobi", "foo bar foobar"]
     >>> references = [["hello there general kenobi", "hello there !"], ["foo bar foobar", "foo bar foobar"]]