This project takes an input file of pdf and by using extractive summarization approach and topic modelling, it extracts various important topics from the pdf text and generates questions on those topics and also generates corresponding answers. These long answers could be summarized using the LDA(Latent Direchlet Allocation) approach. This application is a web application, has a voice assistant integrated for wikipedia searches and google searches.
The name of the project is text_project
This project is developed using django framework with NLP libraries. You can find the exact versions of the libraries in requirements.txt.
This project is under development and everyone is welcome for suggestions and additions.