Added description

semf1.py

@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-# TODO: Add test cases, Provide an option to pass batch size when computing the embeddings
+# TODO: Add test cases, Remove tokenize_sentences flag since it can be determined from the input itself.
 """SEM-F1 metric"""
 
 import abc
@@ -58,19 +58,51 @@ _KWARGS_DESCRIPTION = """
 SEM-F1 compares the system generated overlap summary with ground truth reference overlap.
 
 Args:
-    predictions: List[List(str)] - List of  predictions where each prediction is a list of sentences.
-    references: List[List(str)] - List of references where each reference is a list of sentences.
+    predictions: list - List of  predictions (Details below)
+    references: list - List of references (Details below)
         reference should be a string with tokens separated by spaces.
     model_type: str - Model to use. [pv1, stsb, use] 
         Options: 
-            pv1 - paraphrase-distilroberta-base-v1 
+            pv1 - paraphrase-distilroberta-base-v1 (Default)
             stsb - stsb-roberta-large 
             use - Universal Sentence Encoder
+    tokenize_sentences: bool - Sentence tokenize the input document (prediction/reference). Default: True.
+    gpu: Union[bool, int] - Whether to use GPU or CPU. 
+        Options: 
+            False - CPU (Default)
+            True - GPU, device 0
+            n: int - GPU, device n
+    batch_size: int - Batch Size, Default = 32.
 Returns:
     precision: Precision.
     recall: Recall.
     f1: F1 score.
     
+There are 4 possible cases for inputs corresponding to predictions and references arguments 
+Case 1: Multi-Ref = False, tokenize_sentences = False
+    predictions: List[List[str]] - List of  predictions where each prediction is a list of sentences.
+    references: List[List[str]] - List of references where each reference is a list of sentences.
+Case 2: Multi-Ref = False, tokenize_sentences = True
+    predictions: List[str] - List of  predictions where each prediction is a document
+    references: List[str] - List of references where each reference is a document
+Case 3: Multi-Ref = True, tokenize_sentences = False
+    predictions: List[List[str]] - List of  predictions where each prediction is a list of sentences.
+    references: List[List[List[str]]] - List of multi-references i.e. [[r11, r12, ...], [r21, r22, ...], ...] 
+                                        where each rij is further a list of sentences
+Case 4: Multi-Ref = True, tokenize_sentences = True
+    predictions: List[str] - List of  predictions where each prediction is a document
+    references: List[List[str]] - List of multi-references i.e. [[r11, r12, ...], [r21, r22, ...], ...]
+                                  where each rij is a document  
+    
+This can be seen in the form of truth table as follows:
+Case | Multi-Ref | tokenize_sentences | predictions     | references
+1    | 0         | 0                  | List[List[str]] | List[List[str]]        
+2    | 0         | 1                  | List[str]       | List[str]              
+3    | 1         | 0                  | List[List[str]] | List[List[List[str]]]
+4    | 1         | 1                  | List[str]       | List[List[str]]      
+
+It is automatically determined whether it is Multi-Ref case Single-Ref case.
+ 
 Examples:
 
     >>> import evaluate