Skip to content

krishna8421/title-generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Title Generation From Human to Human Conversation

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.

Dataset

The model is trained on the multiwoz dataset.

The cleaned dataset is available at krishna8421/chats_with_title (6k conversations).

Model

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.

Setup

To run the model, 1st you will need to install the dependencies using the following command:

pip install -r requirements.txt

Usage

Change the input_text variable in the app.py file to the conversation for which you want to generate the title.

python app.py

The model will generate a title for the conversation and print it to the console.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages