EBernhardson claimed this task. EBernhardson added a comment.
Few ideas for future exploration: - Lots of the weights in the tuning report claim to have minimal influence on the final output, look into why. Do we need to collect more negative samples in the training set? Are the features useless? - Could be interesting to generate the sensitivity portion of the report against current production deployed values. - The improvement levels are surprisingly similar to before, perhaps suspisously so. Would also be interesting to re-run the optimization process after deploying the new values. If training with the optimized values as the comparison we should see little if any improvement. If it still shows significant improvements there could be errors in the reporting. TASK DETAIL https://phabricator.wikimedia.org/T306644 EMAIL PREFERENCES https://phabricator.wikimedia.org/settings/panel/emailpreferences/ To: EBernhardson Cc: Aklapper, Smalyshev, dcausse, Liuxinyu970226, EJoseph, EBernhardson, Astuthiodit_1, karapayneWMDE, Invadibot, MPhamWMF, maantietaja, CBogen, ItamarWMDE, Akuckartz, Nandana, Lahi, Gq86, GoranSMilovanovic, QZanden, EBjune, LawExplorer, _jensen, rosalieper, Scott_WUaS, Wikidata-bugs, aude, Mbch331
_______________________________________________ Wikidata-bugs mailing list -- wikidata-bugs@lists.wikimedia.org To unsubscribe send an email to wikidata-bugs-le...@lists.wikimedia.org
