Question generation from the paragraphs/sentences

[glitchinamatrix]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title :
Question generation from a text integrated with fast api
🔴 Aim :
To help teachers for faster question paper preparation
🔴 Dataset :

🔴 Approach : https://medium.com/@shrutisharma.infinity/fastqgen-fastapi-powered-question-generator-1816a43b11d9

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

🔴🟡 Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name : R Divya Sruthi
• GitHub Profile Link : https://github.com/glitchinamatrix
• Email ID : sruthi9.r@gmail.com
• Participant ID (if applicable):
• Approach for this Project :
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

Hi @glitchinamatrix what are the models you are planning to implement here?

[glitchinamatrix]

“ Transformers” to analyse the Text/Sentence provided as an input and to provide questions based on the difficulty level we require. Transformers can process entire input data at once, capture context and relevance, and handle longer sequences efficiently. They are also able to overcome the vanishing gradients problem that recurrent neural networks (RNNs) face.

…

On Sat, 23 Nov 2024 at 10:11 AM, Abhishek Sharma ***@***.***> wrote: Hi @glitchinamatrix <https://github.com/glitchinamatrix> what are the models you are planning to implement here? — Reply to this email directly, view it on GitHub <#989 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BBCWXIUYJKVTQDKNTJR2RSL2CABQJAVCNFSM6AAAAABSD7CQMWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDIOJVGMYDMNJYGQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[abhisheks008]

RNN is a good option to go with. Apart from RNN any other methods/models/architectures as you need to implement at least 3 of these and make a comparison to find the best fitted one based on the accuracy scores.