ENCAPS

A text summarizing and question generating web app created using state-of-the-art Artificial Intelligence and Natural language processing.

Comment

Inspiration :

During these challenging times of the global pandemic, Students face a lot of problems as they are limited to just online classes. In an online class of 200 students, each student does not get the attention that he or she requires. So a lot of their doubts and problems remain unanswered and they are unable to properly learn. Another Problem faced by them is that in this online format, they tend to procrastinate a lot and keep all their tasks till the last time including their lessons, assignments etc which tend to hamper their actual productivity and also their grades. So they need a medium to help prepare in the last crucial moments or at least revise before their tests.

What it does :

“ENCAPS” aims to provide solutions to all the above-mentioned problems.

  • We provide an easy interface where students can either provide an image of their books or notes, links to pages of interests or can directly provide a paragraph and our program will provide a summary of the text (with the option of the length of the summary) which will highly benefit them for reading and last minute revision. The text is extracted using the pytesseract and OpenCV module.
  • Based on the images or links or paragraphs provided by the user, we provide them with a quiz generated using transformers upon the topic given in the texts provided by them and they can have this quiz for their practice.

How we built it :

  • Python Base Programming Language

  • OpenCv and Pytesseract for OCR implementation

  • BeautifulSoup4 as a text parser

  • NLTK for text summarization

  • Transformer Networks for Q/A Generation

  • HTML, CSS, flask for website

  • Google Cloud Platform for hosting the website on a public server

Challenges we ran into :

  • This was the first time we used flask for making a full stack project so we had to learn that properly and we had to face various problems while debugging.
  • This was the first time we used GCP(Google Cloud Platform) platform for deploying our website. It was really difficult and our CPU crashed many times while deploying, which was again a major problem.

Accomplishments that we are proud of :

  • We could make a full stack project and implement everything we had thought of.
  • We learnt GCP for the first time and we are happy that we could deploy our website on it and get our own domain.

What we learnt :

  • We learnt using flask for linking our front end and our ML model.
  • We learnt using GCP platform for deploying our website on a public server.
  • We learnt the concept of using NLP and transformers for Q/A generation and summarization.

What's next for ENCAPS?

We are thinking of adding new features to our website and enhancing the model used in our website if it would help in providing much better results.

Built With

Share this project:

Updates