Update README.md

pcll/README.md

@@ -1,14 +1,14 @@
 # PCLL
 ## Introduction
------
+
 PCLL (Prompt-Conditioned Lifelong Learning) is build by Conversational AI Team, Alibaba DAMO Academy.
 
 The corresponding paper has been published at EMNLP 2022 main conference: "***Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue***".
 
 ## PCLL Implementation 
------
+
 ### Requirements
-```
+```bash
 pip install -r requirements.txt
 ```
 ### Dataset
@@ -17,20 +17,23 @@ Put the required datasets for intent detection and slot filling tasks under the
 The datasets process scripts are also contained `DATA`. You can read the files for more details.
 
 ### Model Training and Evaluation
-```
+```bash
 sh scripts/intent_all_train.sh # for lifelong intent detection task
 sh scripts/slot_all_train.sh # for lifelong slot filling task
 ```
 The files required for training are `lltrain.py, mycvae/model.py, mycvae/trainer.py`
 
 ## Citation
----- 
-If you use our code or find PCLL useful for your work, please cite our paper as:\
-@inproceedings{zhao2022cvae,\
+
+If you use our code or find PCLL useful for your work, please cite our paper:
+
+```bibtex
+@inproceedings{zhao2022cvae,
   title={Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue},
   author={Zhao, Yingxiu and Zheng, Yinhe and Tian, Zhiliang and Gao, Chang and Yu, Bowen and Yu, Haiyang and Li, Yongbin and Sun, Jian and Zhang, Nevin L.},
   booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
-  year={2022},\
+  year={2022},
 }
+```