metadata

title: SummaryProject
sdk: docker
app_file: src/api.py
pinned: false

Project Deep Learning - Text Summarisation tool and it's application programming interface

As part of the master course "Neural Network", for this university project, our task is about creating an application, an interface or a python library in the use of NLP (Natural Language Processing) with the help of an artificial neural network system.

Description

Objectives of our project :

Create an interface which allows users to summarize a long text like press article into a brief version.

To achieve this general objective, for the algorithm part, we would like to test two different deep learning methods : setting up a LSTM model and fine tuning a transformer model.

For the interface part, we wanted to create an interface building with a fastAPI framework and put the application on Huggingface.

Getting Started

Get prepared

Open the link below directing towards our interface on huggingface.

https://huggingface.co/spaces/EveSa/SummaryProject

The interface

1- Choose a model for your summarization task (LSTM/Fine-tuned T5) by clicking on the scroll-down list. And click the Select model button.
2- Enter your text to summarize in the left section.
3- Click on 'Go!' botton and you will get your summary!
4- Don't forget to reset the app for your next try. The botton is at the right next to 'Go!'.

In case you want to try to execute our scripts :

Get prepared

In order to run the script, you need to :
1- Create a virtual environment named .venv

python3 -m virtualenv .venv
source .venv/bin/activate

2- Also install the dependencies

pip install -U -r requirements.txt

You are now ready to execute the scripts

The program api.py

Run the script with the command below :

python3 api.py

This code generates the same page as on Huggingface in your browser. To do the task, you may follow the steps in the previous section.

Authors

Eve SAUVAGE

Estelle SALMON

Lingyun GAO

License

This project is licensed under the [M2 TAL] License