Update README.md

README.md

@@ -40,14 +40,14 @@ predictions = [
     {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
   ]
 ]
-evaluation_scores = module.compute(predictions=predictions, references=references)
+evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict")
 ```
 
 ### Inputs
-- **predictions** (`list` of `list` of `dictionary`): relation and its type of prediction
-- **references** (`list` of `list` of `dictionary`): references for each relation and its type
-- **mode** (`str`): define strict or boundaries mode
-- **only_all** (`bool`): define whether only output ["ALL"] relation_type score or every relation_type score, default True
+- **predictions** (`list` of `list` of `dictionary`): a list of list of dictionary with every element's relation_type and their entity name
+- **references** (`list` of `list` of `dictionary`): a list of list of dictionary with every element's relation_type and their entity name
+- **mode** (`str`): define strict or boundaries mode for evaluation, strict mode consider "head_type" and "tail_type", boundaries mode doesn't consider "head_type" and "tail_type"
+- **only_all** (`bool`): True for only output ["ALL"] relation_type score. False for output every relation_type score, default True
 - **relation_types** (`list`): define relation type that need to be evaluate, if not given, it will construct relation_types from ground truth, default []
  
 ### Output Values
@@ -79,25 +79,58 @@ Output Example:
 Remind : Macro_f1、Macro_p、Macro_r、p、r、f1 are always a number between 0 and 1. And tp、fp、fn depend on how many data inputs.
 
 ### Examples
-Example of only one prediction and reference:
+Example1 : only one prediction and reference, mode = strict, consider only output ALL relation score
 ```python
 metric_path = "Ikala-allen/relation_extraction"
 module = evaluate.load(metric_path)
 references = [
   [
-    {"head": "phip igments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+    {"head": "phipigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+    {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+    {'head': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
+  ]
+]
+
+# Example references (ground truth)
+predictions = [
+  [
+    {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+    {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+  ]
+]
+
+# Calculate evaluation scores using the loaded metric
+evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict", only_all=True,relation_types = [])
+
+print(evaluation_scores)
+>>> {'tp': 1, 'fp': 1, 'fn': 2, 'p': 50.0, 'r': 33.333333333333336, 'f1': 40.0, 'Macro_f1': 25.0, 'Macro_p': 25.0, 'Macro_r': 25.0}
+```
+
+Example2 : only one prediction and reference, mode = boundaries, consider only output ALL relation score
+```python
+metric_path = "Ikala-allen/relation_extraction"
+module = evaluate.load(metric_path)
+references = [
+  [
+    {"head": "phipigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
     {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
+    {'head': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
   ]
 ]
+
+# Example references (ground truth)
 predictions = [
   [
     {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
     {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
   ]
 ]
-evaluation_scores = module.compute(predictions=predictions, references=references)
+
+# Calculate evaluation scores using the loaded metric
+evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict", only_all=True,relation_types = [])
+
 print(evaluation_scores)
->>> {'sell': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0}, 'ALL': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}}
+>>> {'tp': 2, 'fp': 0, 'fn': 1, 'p': 100.0, 'r': 66.66666666666667, 'f1': 80.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}
 ```
 
 Example with two or more prediction and reference: