This epic task covers the work under KR WE2.1 to develop a model for assigning countries to Wikipedia articles as a concrete step towards improving our topic infrastructure and the recommender systems that use it. It builds on the planning the started under T361637.

Hypothesis text:

If we build a country-level inference model for Wikipedia articles, we will be able to filter lists of articles to those about a specific region with >70% precision and >50% recall.

Documentation: https://meta.wikimedia.org/wiki/Research:Language-Agnostic_Topic_Classification/Countries