Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gaizkiaadeline/extractive-summarization-of-news-articles
A project on extractive summarization of news articles using top 3 and top 5 sentence extraction methods, evaluated with Rouge Score. The project includes detailed analysis of the generated summaries’ quality.
https://github.com/gaizkiaadeline/extractive-summarization-of-news-articles
Last synced: 1 day ago
JSON representation
A project on extractive summarization of news articles using top 3 and top 5 sentence extraction methods, evaluated with Rouge Score. The project includes detailed analysis of the generated summaries’ quality.
- Host: GitHub
- URL: https://github.com/gaizkiaadeline/extractive-summarization-of-news-articles
- Owner: gaizkiaadeline
- Created: 2024-10-16T15:19:48.000Z (23 days ago)
- Default Branch: main
- Last Pushed: 2024-10-22T03:09:02.000Z (17 days ago)
- Last Synced: 2024-10-22T21:36:01.397Z (16 days ago)
- Language: Jupyter Notebook
- Size: 1 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Extractive Summarization of News Articles Using Top 3 and Top 5 Sentence Scoring with Rouge Score Evaluation
This project applies extractive summarization techniques to a set of three news articles. The summarization process uses a sentence scoring approach, where the top 3 and top 5 highest-scoring sentences from each article are extracted to form the summary. The summaries are then evaluated using the Rouge Score to measure their quality by comparing them to reference summaries.
**The project includes:**
- Text Preprocessing: Tokenization and sentence splitting to prepare the news articles for summarization.
- Summarization Model: Extraction of the top 3 and 5 sentences based on scoring algorithms from each news article.
- Evaluation: The Rouge Score is used to evaluate the generated summaries in terms of recall, precision, and F1-score.
- Analysis: Detailed analysis of the performance of the summarization models using both top 3 and top 5 sentence extraction methods.
**Key Features:**
- Implementation of an extractive summarization method specifically for news articles.
- Evaluation of generated summaries using Rouge Score metrics.
- Comparison of results between top 3 and top 5 sentence extraction.
- In-depth analysis of the quality and effectiveness of the summaries.
**Technologies Used:**
- Python: For data processing and model development.
- NLTK / SpaCy: For text preprocessing and tokenization.
- Rouge Score: For summarization evaluation.
