https://github.com/saif807380/text-summariser
A simple document summariser. Uses SpaCy to perform extractive summarisation of the document
https://github.com/saif807380/text-summariser
Last synced: 3 months ago
JSON representation
A simple document summariser. Uses SpaCy to perform extractive summarisation of the document
- Host: GitHub
- URL: https://github.com/saif807380/text-summariser
- Owner: Saif807380
- License: mit
- Created: 2020-03-06T05:10:34.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-03-11T14:50:50.000Z (over 5 years ago)
- Last Synced: 2025-04-04T09:31:53.202Z (6 months ago)
- Language: Jupyter Notebook
- Size: 8.79 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Text-Summariser
A simple document summariser. Uses SpaCy to perform extractive summarisation of the document
## Preprocessing
All the stop words are eliminated from the original text.
## Algorithm
1. The word frequency for each word in the document is calculated. Each of the frequencies is divided by the max frequency to normalize the frequencies.
2. A dictionary consisting of the sentence and it's corresponding sentence score is generated. The sentence scores are calculated by taking the average of the normalized word frequencies of each word appearing in the sentence.
3. The dictionary is sorted in decreasing order of sentence score which is an indicator of importance of a given sentence in context of the document.
4. The top N sentences are displayed in the summary in the order of appearance in the original document.
## License
[MIT](https://choosealicense.com/licenses/mit/)