Update README.md

README.md

@@ -32,28 +32,13 @@ Tested with `tensorflow 2.3.1, transformers 4.1.1, torch 1.6.0`
 If you use this checkpoint in your work, please cite:
 
 ``` latex
-@inproceedings{mukherjee-hassan-awadallah-2020-xtremedistil,
-    title = "{X}treme{D}istil: Multi-stage Distillation for Massive Multilingual Models",
-    author = "Mukherjee, Subhabrata  and
-      Hassan Awadallah, Ahmed",
-    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
-    month = jul,
-    year = "2020",
-    address = "Online",
-    publisher = "Association for Computational Linguistics",
-    url = "https://www.aclweb.org/anthology/2020.acl-main.202",
-    doi = "10.18653/v1/2020.acl-main.202",
-    pages = "2221--2234",
+@misc{mukherjee2021xtremedistiltransformers,
+      title={XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation}, 
+      author={Subhabrata Mukherjee and Ahmed Hassan Awadallah and Jianfeng Gao},
+      year={2021},
+      eprint={2106.04563},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
 }
 ```
 
-``` latex
-@misc{wang2020minilm,
-    title={MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers},
-    author={Wenhui Wang and Furu Wei and Li Dong and Hangbo Bao and Nan Yang and Ming Zhou},
-    year={2020},
-    eprint={2002.10957},
-    archivePrefix={arXiv},
-    primaryClass={cs.CL}
-}
-```