WetSuite will be a web-portal and a collection of tools and resources to accelerate the application of Natural Language Processing (NLP) methods to Dutch and EU governmental legal data. WetSuite will provide data access and tools both for researchers in law with little or no programming experience, and for researchers in NLP with little or no legal background. It will empower individual researchers, facilitate interdisciplinary collaborations, and serve as a stepping stone for legal scholars and students interested in NLP.
Data access
WetSuite will build on existing government repositories to provide convenient access to Dutch and EU laws/regulations and court judgments, Dutch administrative decisions, as well as related textual data. We take an integrated approach towards the three branches of government – legislator, courts and administration – as they cannot be fully understood in isolation.
Tools
Besides data preprocessing and conversion, WetSuite will offer an interface to powerful NLP libraries, attuned to the different data types. Common NLP methods will be made available as web services in the browser, with no installation or programming required. The underlying WetSuite Python library will be open source and easily extensible for users with technical know-how.
Please stay tuned while WetSuite is in active development!
If you have particular infrastructural needs in the domain of legal data/NLP, let us know.
Get wet!
Are you interested in applying NLP to legal data? Do not hesitate to get in touch!
WetSuite is made possible by funding from PDI-SSH, awarded to a proposal by Anne Meuwese (PI), Matthijs Westera, Alex Ingrams and Stephan Raaijmakers from Leiden University, Johan Wolswinkel from Tilburg University, and Gijs van Dijck from Maastricht University.
[Image source: https://nl.wikipedia.org/wiki/Wetsuit#/media/Bestand:Shorty_wetsuit.jpg by BoaNoite]