Title Generation model for human to human conversation generates a title for a conversation between humans. The model is trained on multiwoz dataset and generates a title for the conversation based on the content of the conversation. The model uses a combination of natural language processing and machine learning techniques to generate the title, and can be used to automatically generate titles for conversations in a variety of contexts.
The model is trained on the multiwoz dataset.
The cleaned dataset is available at krishna8421/chats_with_title (6k conversations).
The model uses the T5 transformer model, which is a state-of-the-art model for natural language processing tasks. The model is fine-tuned on the multiwoz dataset to generate titles for human to human conversations.
To run the model, 1st you will need to install the dependencies using the following command:
pip install -r requirements.txtChange the input_text variable in the app.py file to the conversation for which you want to generate the title.
python app.pyThe model will generate a title for the conversation and print it to the console.