https://github.com/nav3005/dl-1-section-1
Projects about Webscraping from WikiHow using Python Library such as Beautiful Soup
https://github.com/nav3005/dl-1-section-1
Last synced: 9 months ago
JSON representation
Projects about Webscraping from WikiHow using Python Library such as Beautiful Soup
- Host: GitHub
- URL: https://github.com/nav3005/dl-1-section-1
- Owner: Nav3005
- Created: 2024-09-08T10:16:45.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-08T10:35:36.000Z (almost 2 years ago)
- Last Synced: 2024-12-27T12:27:09.367Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 10 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Learning
## Section 1: Introduction to Blog Generation using Language Models
### Overview
This section covers the basics of using language models to generate blog content. The focus is on fine-tuning a pre-trained model to generate subheadings for given paragraphs. Web scraping is employed to create a dataset by extracting content from WikiHow.
### Steps
1. **Language Models**: Understand how language models are used for text generation in natural language processing (NLP).
2. **Fine-Tuning**: Learn the process of fine-tuning a pre-trained model for specific tasks like generating subheadings for blog content.
3. **Web Scraping**: Use BeautifulSoup to scrape paragraphs and subheadings from WikiHow and create a dataset.
4. **Dataset Creation**: Compile the scraped data into a CSV file for use in the fine-tuning process.
### Tools Used
- **BeautifulSoup**: Python library for web scraping.
- **Requests**: For making HTTP requests to fetch webpage content.
- **CSV**: To store the scraped data in a structured format.