Update README.md

README.md

@@ -33,13 +33,18 @@ I'm interested in using encoder-based extraction of named legal document section
 
 ### Using ROBERTA for segmentation involves combining sentences A and B into single input to ROBERTA. See below:
 
-[cls] A [sep] B
+1. standard ROBERTA model on pairwise sentences ((512 / 2) - 3 tokens, max, per sentence)
+
+[cls] A [sep] B [SEP]
 
 and the embedding for [cls] can be used in a binary classifier.
 
 ### But, the architecture used here (implemented via ) is:
 
-1. standard ROBERTA model
+1. standard ROBERTA model, but instead input is just
+
+[CLS] A [SEP]
+
 2. classification of [CLS] token embedding:
 
 ```