https://github.com/pacifio/fas_rst
Document Summarisation bot for Falcon Academy
https://github.com/pacifio/fas_rst
bot nlp pdf text-summarization
Last synced: about 2 months ago
JSON representation
Document Summarisation bot for Falcon Academy
- Host: GitHub
- URL: https://github.com/pacifio/fas_rst
- Owner: pacifio
- License: mit
- Created: 2022-08-02T15:01:03.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-08-07T00:52:41.000Z (almost 4 years ago)
- Last Synced: 2026-03-30T06:29:10.692Z (3 months ago)
- Topics: bot, nlp, pdf, text-summarization
- Language: Python
- Homepage: https://falconacademyofsciences.org/
- Size: 567 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
## Document Summarisation bot for Falcon Academy
## What is `fas_rst`
FAS is the shorthand for Falcon Academy of Sciences and RST stands for Research paper Summarisation Tool , written in pure python leveraging the `spacy` library
## How to run
Paste the commands below to your terminal
```bash
git clone https://github.com/pacifio/fas_rst
cd fas_rst
pip install -r requirements.txt
python3 main.py mypdf.pdf
```
Please note that the `main.py` takes one argument which is the filename , replace `mypdf.pdf` with your filename , the text extracted from your pdf will be saved to `original.txt` and the summmary will be saved to `summary.txt`
## Further plans
- [ ] Use `BART` NLP model
- [ ] Better replacement for the `tika` library cause it's dependent on JAVA
- [ ] More arguments to the script to accept generic text files , can be used for any sort of textual summarization
> version 0.0.1