diff --git a/learnware/config.py b/learnware/config.py
index fb78a08..8bd557e 100644
--- a/learnware/config.py
+++ b/learnware/config.py
@@ -80,19 +80,13 @@ semantic_config = {
         "Values": [
             "Classification",
             "Regression",
-            "Clustering",
             "Feature Extraction",
-            # "Generation",
             "Segmentation",
             "Object Detection",
             "Others",
         ],
         "Type": "Class",  # Choose only one class
     },
-    # "Device": {
-    #     "Values": ["CPU", "GPU"],
-    #     "Type": "Tag",
-    # },  # Choose one or more tags
     "Library": {
         "Values": ["Scikit-learn", "PyTorch", "TensorFlow", "Others"],
         "Type": "Class",
diff --git a/learnware/market/easy2/checker.py b/learnware/market/easy2/checker.py
index 589f3e2..5e455a7 100644
--- a/learnware/market/easy2/checker.py
+++ b/learnware/market/easy2/checker.py
@@ -43,7 +43,7 @@ class EasySemanticChecker(BaseChecker):
                     assert int(k) >= 0 and int(k) < dim, f"Dimension number in [0, {dim})"
                     assert isinstance(v, str), "Description must be string"
 
-            if semantic_spec["Task"]["Values"][0] in ["Classification", "Regression", "Feature Extraction"]:
+            if semantic_spec["Task"]["Values"][0] in ["Classification", "Regression"]:
                 assert semantic_spec["Output"] is not None, "Lack of output semantics"
                 dim = semantic_spec["Output"]["Dimension"]
                 for k, v in semantic_spec["Output"]["Description"].items():
@@ -126,7 +126,7 @@ class EasyStatChecker(BaseChecker):
                 logger.warning(f"learnware {learnware} prediction method is not valid!")
                 return self.INVALID_LEARNWARE
 
-            if semantic_spec["Task"]["Values"][0] in ("Classification", "Regression", "Feature Extraction"):
+            if semantic_spec["Task"]["Values"][0] in ("Classification", "Regression"):
                 # Check output type
                 if isinstance(outputs, torch.Tensor):
                     outputs = outputs.detach().cpu().numpy()