Update README.md

README.md

@@ -12,8 +12,7 @@ Language model of the pre-print arXiv paper titled: "_**miCSE**: Mutual Informat
 
 
 # Brief Model Description
-The **miCSE** language model is trained for sentence similarity computation. Training the model imposes alignment between the attention pattern of different views (embeddings of augmentations) during contrastive learning. Learning sentence embeddings with **miCSE** entails enforcing the syntactic consistency across augmented views for every single sentence, making contrastive self-supervised learning more sample efficient. This is achieved by regularizing the attention distribution. Regularizing the attention space enables learning representation in self-supervised fashion even when the _training corpus is comparatively small_. This is particularly interesting for _real-world applications_, where training data is significantly smaller than commonly used corpora like Wikipedia.
-
+The **miCSE** language model is trained for sentence similarity computation. Training the model imposes alignment between the attention pattern of different views (embeddings of augmentations) during contrastive learning. Intuitively, learning sentence embeddings with miCSE entails enforcing __syntactic consistency across dropout augmented views__. Practically, this is achieved by regularizing the self-attention distribution. By regularizing self-attention during training, representation learning becomes much more sample efficient. Hence, self-supervised learning becomes tractable even when the training set is limited in size. This property makes miCSE particularly interesting for __real-world applications__, where training data is typically limited.
 # Model Use Cases
 The model intended to be used for encoding sentences or short paragraphs. Given an input text, the model produces a vector embedding capturing the semantics. Sentence representations correspond to embedding of the _**[CLS]**_ token. The embedding can be used for numerous tasks such as **retrieval**,**sentence similarity** comparison (see example 1) or **clustering** (see example 2).