The paper "Growing Wikipedia Across Languages via Recommendation" ([[ https://arxiv.org/pdf/1604.03235.pdf | pdf ]]) has a section (section 2.2) about ranking missing articles.
== A/C ==
[x] Figure out which of the features in Section 2.2. we can compute at scale and on a regular basis.
See T190774#4192169.
[x] Take the features from the previous step and use the model in Section 2.2. to build a prediction algorithm for every language.
- Repository for training models and making predictions: https://github.com/wikimedia/research-translation-recommendation-models
- Predictions for 05/31/2018 for the top 10 language pairs according to Conten Translation: https://github.com/wikimedia/research-translation-recommendation-predictions
[ ] Discuss how to surface recommendations.
See T190774#4189253 for details.
== Previous work ==
# https://github.com/schana/recommendation-translation