General Suggestions for Onboarding
Applicants are encouraged to read the documentation about the Research Project [1][2], and become familiar with the codebase for the machine learning models [3], as well as with basic notions and functions of the Keras library for Python [4].
Actual Onboarding Task
As an onboarding task to get started with the project, we would suggest to become familiar with machine learning component of the framework. Clone the repository [3], install the libraries required, and work with the provided models to classify a few statements taken from Wikipedia articles. Models are available for English, Italian, and French Wikipedia. Feel free to chose your favorite language. Please ping @Miriam here if you need any help.
[1] https://meta.wikimedia.org/wiki/Research:Identification_of_Unsourced_Statements
[2] https://arxiv.org/pdf/1902.11116.pdf
[3] https://github.com/mirrys/citation-needed-paper
[4] https://keras.io
[5] https://phabricator.wikimedia.org/