Update README.md

README.md

@@ -33,7 +33,7 @@ First, we pretrain **CXR-BERT-general** from a randomly initialized BERT model v
 
 ```
 @misc{https://doi.org/10.48550/arxiv.2204.09817,
-  title = {Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing},
+  title = {Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing},
   author = {Boecking, Benedikt and Usuyama, Naoto and Bannur, Shruthi and Castro, Daniel C. and Schwaighofer, Anton and Hyland, Stephanie and Wetscherek, Maria and Naumann, Tristan and Nori, Aditya and Alvarez-Valle, Javier and Poon, Hoifung and Oktay, Ozan},
   publisher = {arXiv},
   year = {2022},
@@ -91,7 +91,7 @@ CXR-BERT also contributes to better vision-language representation learning thro
 | **BioViL**                         | **CXR-BERT** |                **1.027**                 |
 | **BioViL-L**                       | **CXR-BERT** |                **1.142**                 |
 
-Additional details about performance can be found in the corresponding paper, [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://arxiv.org/abs/2204.09817).
+Additional details about performance can be found in the corresponding paper, [Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing](https://arxiv.org/abs/2204.09817).
 
 ## Limitations
 
@@ -99,4 +99,4 @@ This model was developed using English corpora, and thus can be considered Engli
 
 ## More Information
 
-Refer to the corresponding paper, [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://arxiv.org/abs/2204.09817) for additional details and performance information.
+Refer to the corresponding paper, [Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing](https://arxiv.org/abs/2204.09817) for additional details and performance information.