Update README.md

README.md

@@ -20,5 +20,14 @@ MobileBERT uses a 128-dimensional embedding layer followed by 1D convolutions to
 If you use this model, please consider citing the following paper:
 
 ```bibtex
-
+@misc{https://doi.org/10.48550/arxiv.2302.04725,
+  doi = {10.48550/ARXIV.2302.04725},
+  url = {https://arxiv.org/abs/2302.04725},
+  author = {Rohanian, Omid and Nouriborji, Mohammadmahdi and Jauncey, Hannah and Kouchaki, Samaneh and Group, ISARIC Clinical Characterisation and Clifton, Lei and Merson, Laura and Clifton, David A.},
+  keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2.7, 68T50},
+  title = {Lightweight Transformers for Clinical Natural Language Processing},
+  publisher = {arXiv},
+  year = {2023},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
 ```