Final version

What we add

Add paper url and source code.

Program information

• dataprepare.py: Data preprocessing
• infer_gpt.py: Infer GPT-2 model with unput text
• infer_score.py: Infer score with input text
• model.py: Score model based on GPT-2 and RoBERTa
• trainRL.py: Train PPO model, using GPT-2 and score model
• traingpt.py: Train GPT-2 model
• trainscore.py: Train score model