Fix medical benchmarks import (#3151)

* Update utils.py

lm_eval/tasks/meddialog/utils.py

@@ -11,7 +11,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/mediqa_qa2019/utils.py

@@ -11,7 +11,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/medtext/utils.py

@@ -11,7 +11,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/meqsum/utils.py

@@ -11,7 +11,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/mimic_repsum/utils.py

@@ -15,7 +15,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py radgraph"
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/mts_dialog/utils.py

@@ -11,7 +11,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/olaph/utils.py

@@ -12,7 +12,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(