Update README.md

README.md

@@ -15,15 +15,15 @@ This model is used to generate paraphrases. It has been trained on a mix of 3 di
 
 We use this model in our ACL'21 Paper ["PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning"](https://arxiv.org/abs/2105.12995)
 
-This model, jointly used with generation constraints, allows to generate diverse paraphrases. We use those paraphrases as a data augmentation technique to further boosts a classification model's generalization capability. Feel free to play with the [code](https://github.com/tdopierre/ProtAugment)!
+Jointly used with generation constraints, this model allows to generate diverse paraphrases. We use those paraphrases as a data augmentation technique to further boosts a classification model's generalization capability. Feel free to play with the [code](https://github.com/tdopierre/ProtAugment)!
 
 If you use this model, please consider citing our paper.
-```bash
+```
 @article{Dopierre2021ProtAugmentUD,
-  title={ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning},
-  author={Thomas Dopierre and C. Gravier and Wilfried Logerais},
-  journal={ArXiv},
-  year={2021},
-  volume={abs/2105.12995}
+    title={ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning},
+    author={Thomas Dopierre and C. Gravier and Wilfried Logerais},
+    journal={ArXiv},
+    year={2021},
+    volume={abs/2105.12995}
 }
 ```