Repository files navigation

This is a simple Jupyter notebook with a demo implementation of the "PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation" paper, to be presented in EACL 2021 SRW.

• Python 3.6.9
• The Python wrapper ofOpenIE5 (has to be installed manually)
• The Python wrapper ofClausIE (has to be installed from source)
• Follow the instructions below for additional requirements.

1. It is recommended to create a new virtual environment to avoid version conflicts. For Linux:

python3 -m venv penelopiesource penelopie/bin/activate

2. Install the OpenIE5 and ClausIE OIE engines following the above links.
3. Install additional requirements with:

git clone https://github.com/lighteternal/PENELOPIE.gitcd PENELOPIEpip install -r requirements.txt

The pipeline showcased in the Jupyter notebook will process the Greek sentences indata/demo_greek.txt, translate them into English, extract triples using 3 OIE engines and back-translate the resulting triples in Greek. The results are found indata/final_triples.csv.The standalone NMT models (EN2EL, EL2EN) can be found here:https://huggingface.co/lighteternal

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Apache2.0