Daily News Text Summarizer using Deep Learning

[Soumya0927]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : Daily News Text Summarizer
🔴 Aim : Develop a system that automatically summarizes news articles, providing concise and relevant information for users to stay updated efficiently.
🔴 Dataset : CNN / DailyMail Dataset containing around 300k unique news articles written by journalists at CNN and the Daily Mail.
🔴 Approach : Text summarization algorithms, such as Extractive Summarization (e.g., TextRank), Abstractive Summarization (e.g., BERT or GPT-based models), and Sequence-to-Sequence models. Conduct Exploratory Data Analysis (EDA) to identify trends, patterns, and key topics before developing the models. Compare algorithm performance based on metrics such as ROUGE scores, and select the best-fit algorithm for generating accurate and concise summaries.

---

📍 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 : Soumya Gupta
• GitHub Profile Link : https://github.com/Soumya0927
• Email ID : [email protected]
• Participant ID (if applicable):
• Approach for this Project : Mentioned above
• What is your participant role? GSSoC'24 extended and Hactoberfest'24

---

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]

Start working on it. Assigned this issue to you @Soumya0927

[Soumya0927]

Hello, @abhisheks008
I apologize for the delay due to some health issues. but am eager to get back on track with this project. I’d appreciate the chance to contribute and continue working on it.
Thank You.

[Kritika75]

Hey, if this issue is not resolved yet, i would like to work on it, can you assign me this?

A little intro about myself:

Hey, I’m Kritika, currently participating in KWOC'24 and also I've participated in GSSOC'24

@abhisheks008

[abhisheks008]

Hey, if this issue is not resolved yet, i would like to work on it, can you assign me this?

A little intro about myself:

Hey, I’m Kritika, currently participating in KWOC'24 and also I've participated in GSSOC'24

@abhisheks008

Hi @Kritika75 can you please share your approach and dataset you are planning to use in this project/issue?

[Kritika75]

Hey, if this issue is not resolved yet, i would like to work on it, can you assign me this?
A little intro about myself:
Hey, I’m Kritika, currently participating in KWOC'24 and also I've participated in GSSOC'24
@abhisheks008

Hi @Kritika75 can you please share your approach and dataset you are planning to use in this project/issue?

Hey, i gonna use that same CNN/DailyMail Dataset as mentioned above in the issue

[shivansh-2003]

Full name : Shivansh Mahajan
GitHub Profile Link : https://github.com/shivansh-2003
Email ID : [email protected]
For the Daily News Text Summarizer project, I would start by performing Exploratory Data Analysis (EDA) to understand article structure and key trends. I would then implement a combination of extractive (e.g., TextRank) and abstractive summarization techniques (e.g., BERT, GPT). Finally, I’d evaluate model performance using ROUGE scores and select the best model for concise summaries.

[abhisheks008]

Full name : Shivansh Mahajan GitHub Profile Link : https://github.com/shivansh-2003 Email ID : [email protected] For the Daily News Text Summarizer project, I would start by performing Exploratory Data Analysis (EDA) to understand article structure and key trends. I would then implement a combination of extractive (e.g., TextRank) and abstractive summarization techniques (e.g., BERT, GPT). Finally, I’d evaluate model performance using ROUGE scores and select the best model for concise summaries.

In which open source event you are participating in?
@shivansh-2003

[shivansh-2003]

SWOC

[abhisheks008]

This issue is for other event. Please check out other issues present here in this repository.

[satyam1024]

Hey,
If this issue is still open, I would love to work on it!

Full Name: Satyam Kathait
GitHub Profile Link: https://github.com/satyam1024
Email ID: [email protected]

Approach for this Project:
I plan to use the dataset from Kaggle for training and evaluation.
Begin by implementing a basic neural network as a baseline.
Progress to more advanced techniques, including attention models and transformer-based architectures (e.g., BERT or GPT).
Fine-tune models to achieve the desired accuracy and performance.
Finally, develop a simple frontend using Streamlit, allowing users to input a news link or paste an article to generate a summary.

Open Source Program: WOC 4.0

Looking forward to contributing to this project!
Best regards,
Satyam Kathait