style: Rename "reasoning" to "common-sense reasoning"

app.py

@@ -100,7 +100,7 @@ the [MMLU](https://doi.org/10.48550/arXiv.2009.03300) and
 [ARC](https://allenai.org/data/arc) datasets. We use the Matthews Correlation
 Coefficient (MCC) as the evaluation metric.
 
-### Reasoning
+### Common-sense Reasoning
 Given a scenario and multiple possible endings, choose the correct ending. As with text
 classification, we use the probabilities of the answer letter (a, b, c or d) to choose
 the answer. The datasets in this task are machine translated versions of the
@@ -164,7 +164,7 @@ class Dataset(BaseModel):
 
 SUMMARISATION = Task(name="summarisation", metric="bertscore")
 KNOWLEDGE = Task(name="knowledge", metric="mcc")
-REASONING = Task(name="reasoning", metric="mcc")
+COMMON_SENSE_REASONING = Task(name="common-sense reasoning", metric="mcc")
 GRAMMAR = Task(name="grammar", metric="mcc")
 READING_COMPREHENSION = Task(name="reading comprehension", metric="em")
 TEXT_CLASSIFICATION = Task(name="text classification", metric="mcc")
@@ -246,14 +246,14 @@ DATASETS = [
     Dataset(name="mmlu", language=ENGLISH, task=KNOWLEDGE),
     Dataset(name="mmlu-fr", language=FRENCH, task=KNOWLEDGE),
 
-    Dataset(name="hellaswag-da", language=DANISH, task=REASONING),
-    Dataset(name="hellaswag-no", language=NORWEGIAN, task=REASONING),
-    Dataset(name="hellaswag-sv", language=SWEDISH, task=REASONING),
-    Dataset(name="winogrande-is", language=ICELANDIC, task=REASONING),
-    Dataset(name="hellaswag-de", language=GERMAN, task=REASONING),
-    Dataset(name="hellaswag-nl", language=DUTCH, task=REASONING),
-    Dataset(name="hellaswag", language=ENGLISH, task=REASONING),
-    Dataset(name="hellaswag-fr", language=FRENCH, task=REASONING),
+    Dataset(name="hellaswag-da", language=DANISH, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-no", language=NORWEGIAN, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-sv", language=SWEDISH, task=COMMON_SENSE_REASONING),
+    Dataset(name="winogrande-is", language=ICELANDIC, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-de", language=GERMAN, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-nl", language=DUTCH, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag", language=ENGLISH, task=COMMON_SENSE_REASONING),
+    Dataset(name="hellaswag-fr", language=FRENCH, task=COMMON_SENSE_REASONING),
 ]