This is part one of a capstone project I completed during the Cambridge Spark bootcamp. The project was proposed by wavelength.law. I made use of Beautiful Soup to extract legal case information from the Bailii.org website. I also used a pretrained Spacy Named Entity Recognition Model called Blackstone, trained on English legal texts, to extract relevant sections and Acts from the legal cases.
My Project report is available here
Spacy 2.1.8 is required to work with blackstone, see the blackstone github page for more detais:
https://github.com/ICLRandD/Blackstone
blackstone.yml file is included for conda environment configuration that worked for me. package verions are below:
spacy version 2.1.8
blackstone version 0.1.15