This is a final report of the work which was done as part of Government Gazette text mining, cross linking, and codification Project (or 3gm for short) using Natural Language Processing Methods and Practices hosted in github.com/eellak/gsoc2018-3gm and 3gm.ellak.gr.

This project aims to provide with the most recent versions of each law, i.e. an automated codex via Natural Language Processing (NLP) methods and practices on Greek Legislation, along with additional functionality such as topic modeling for similarity analysis, versioning system in MongoDB, continuous integration tools & scripts and a web application. The accuracy of detecting amendments on Greek Legislation texts was 89%.

A more detailed explanation of the project is located at the Wiki Home Page.

To read more about the project, please visit the project repository or the demonstration page

An extensive documentation is provided at the README and the project wiki.

All of my work can be found at the project repository which was created from scratch and does not rely on any previous code. My commits can be found here.

The deliverables and production ready tools can be over-viewed in this README section along with Installation Instructions.

Throughout the project, I kept weekly project progress report logs, which can be found here.

The project is hosted at 3gm.ellak.gr

Some recommendations for future work can be found here along with any issues that emerge during development.