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 procastinate 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 atleast revise before their tests.
What it does
“ABRIDGE” aims to provide solutions to all the above mentioned problems.
A)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 an paragraph and our program will provide an 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 pytessearct and opencv module.
B)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 their quiz for practice. This webapp will surely help the student undestand the concepts in nutshell and have them enough practice out of it.
C)It has a Text to Speech Google API which aimed to help visually impaired people to learn.
D)This can also be used to summarise the long Terms and Conditions into a small paragraph which enables to know the terms and conditions easily which usually we skip.
How I 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 for frontend and flask for backend
Challenges I ran into
1) 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 integrating the code.
2) The Question Generation model sometimes caused our laptop to crash as it was a very large model.
Accomplishments that I'm proud of
What I learned
Deployment of ML model using Flask backend, it was something we did for the first time.
What's next for ABRIDGER
We plan to generate personalised summaries for the user , allow to save the summaries and question and answers for future use and also have multiple language support.