These notebooks have been designed to help getting started with the processing of historical text resources (from Europeana Newspapers) with natural language processing (NLP) tools (from CLARIN) using Jupyter notebooks.
The easiest way to get started is to click the Launch binder badge above. This will guide you through the process of creating your own Jupyer instance where you can interactively discover ways of accessing and querying metadata, analysing text resources within notebooks, and using advanced NLP tools on your own selection of newspaper texts.
You can use these notebooks in any local or remote environment that you have access to. Two alternatives to the binder based solution are:
-
installing Anaconda, which offers a user-friendly interface and makes it possible to set up a local Jupyter instance with a few clicks, and
-
jupyter-repo2docker, which offers an easy way to create a docker image based on this repository for those with access to an environment where docker is available.
For more information, you can also have a look at start.ipynb right here.
These training materials have been developed by Twan Goosen and Michał Gawor (CLARIN ERIC) in the context of the Europeana DSI-4 project.
Thanks to Alba Irollo (Europeana), Dieter Van Uytvanck (CLARIN ERIC) and Iulianna van der Lek-Ciudin (CLARIN ERIC) for their contributions.
Learn more about these and other notebooks, and how to use them with language data and technology at clarin.eu/notebooks.
The materials in this repositoy are released under a CC0 1.0 licence.