How to take the keywords from the given dataset to train GPT-2 based chatbot?

I am working with a dataset that contains Questions on various Events conducted by a college and the corresponding answers for the queries. I am using this dataset to train a GPT-2 355M model to create a chatbot where users can get their queries answered. But i am not getting good results and i feel that's because the questions in the dataset are in the -Query format.

For example, Ques: Cicada3302 - Do I need to have any prerequisite knowledge to enter this event

I am confused as to how can I make the chatbot understand that the first words before the - is like a keyword for rest of the question ? I am really new to this, so any help will be appreciated.

I have used the gpt_2_simple library for this. I am attaching the colab link I have written so far, if it might be of any help.

https://colab.research.google.com/drive/1CrzwC9WQwF4YsqD66TY8F7ovTSHKsnFv?usp=sharing