Hey,

This is the 21st weekly update from revision scoring team that we have sent to this mailing list.

New development

• We received a request to get moving on Spanish Wikibooks support, so we dug in:

• We deployed a new Wiki labels campaign[1]

• We fixed an issue in Wiki labels that prevented requests from *.wikibooks.org[2]

• We trained a basic "revert" detection model that seems to be pretty effective[3]

• We also generated a dataset of article quality scores for English Wikipedia[4].  You can download it here: [5]

This week, we invested in some long term tasks.  If you review our phabricator board, you'll see substantial progress in improving our damage detection models with hashing vectorization strategies[6, 7], implementing a more robust model testing strategy[8], and implementing some advance natural language processing strategies[9, 10].  Stay tuned for the completion of these activities in the coming weeks.  

1. https://phabricator.wikimedia.org/T143962 -- Add uniqueness constraints to ores_classification

2. https://phabricator.wikimedia.org/T145406 -- Fix CORS for wikibooks

3. https://phabricator.wikimedia.org/T145428 -- Train/test reverted model for Spanish Wikibooks

4. https://phabricator.wikimedia.org/T135684 -- Generate recent article quality scores for English Wikipedia

5. https://datasets.wikimedia.org/public-datasets/enwiki/article_quality/wp10-scores-enwiki-20160820.tsv.bz2

6. https://phabricator.wikimedia.org/T128087 -- [Spike] Investigate HashingVectorizer

7. https://en.wikipedia.org/wiki/Feature_hashing

8. https://phabricator.wikimedia.org/T142953 -- Train on all data, Report test statistics on cross-validation

9. https://phabricator.wikimedia.org/T144636 -- Implement PCFG features

10. https://en.wikipedia.org/wiki/Stochastic_context-free_grammar

Sincerely, 

Aaron from the Revision Scoring team