[06:42:14] 10Jade, 10Scoring-platform-team: Narrow the Jade box that appears when undoing an edit - https://phabricator.wikimedia.org/T256800 (10kevinbazira) a:03kevinbazira [06:42:52] 10Jade, 10Scoring-platform-team (Current): Narrow the Jade box that appears when undoing an edit - https://phabricator.wikimedia.org/T256800 (10kevinbazira) [11:56:11] (03PS1) 10Nikerabbit: Revert "Localisation updates from https://translatewiki.net." [extensions/ORES] - 10https://gerrit.wikimedia.org/r/612312 [12:59:39] 10Scoring-platform-team, 10Wikidata, 10Wikidata-Query-Service, 10articlequality-modeling, 10artificial-intelligence: Add ORES article quality predictions to the WDQS - https://phabricator.wikimedia.org/T257341 (10dcausse) p:05Triage→03Low As we try to split the graph as much as we can I think the pro... [13:34:15] (03Merged) 10jenkins-bot: Revert "Localisation updates from https://translatewiki.net." [extensions/ORES] - 10https://gerrit.wikimedia.org/r/612312 (owner: 10Nikerabbit) [13:34:43] o/ [13:48:35] Hello Aaron [13:48:46] halfak: [13:48:52] Saw your Github comment [13:49:02] Hey! [13:49:09] I also noticed something in my build, so rebuilding for the 20000 cutoff again [13:49:29] The feature_list was still pointing to the old embeddings [13:49:38] Aha! That would make a big difference! [13:49:49] Yeah. On it. [13:50:19] Hoping the change I made to it doesn't break something though, because I passed in the direct path to it. [13:50:40] It should be done soon [13:53:18] haksoat, should be fine, but you can just move the files into the word2vec folder :P [13:58:50] Haha [13:58:52] True [13:59:39] Didn't want to tamper with the existing files there :-D [16:29:11] 10ORES, 10Scoring-platform-team, 10Operations, 10Release Pipeline (Blubber): Build blubber file for ORES - https://phabricator.wikimedia.org/T210268 (10Halfak) [16:29:32] 10Jade, 10Scoring-platform-team, 10CommRel-Specialists-Support (Apr-Jun-2020): Design Jade pilot deployment plan with the Scoring Platform team - https://phabricator.wikimedia.org/T246486 (10Halfak) a:05Halfak→03None [16:33:52] 10Jade, 10Scoring-platform-team, 10drafttopic-modeling: Add the topic taxonomy to Jade - https://phabricator.wikimedia.org/T257681 (10Halfak) p:05Triage→03Medium [16:36:18] 10Scoring-platform-team, 10editquality-modeling, 10artificial-intelligence: Update Turkish Wikipedia's labeling campaign for 2020 - https://phabricator.wikimedia.org/T257359 (10Halfak) p:05Triage→03Medium @calbon this is the Wikilabels task we talked about at backlog grooming. [16:36:51] 10ORES, 10Scoring-platform-team (Current), 10Growth-Scaling, 10Growth-Team, and 2 others: Add articletopic model to testwiki - https://phabricator.wikimedia.org/T257248 (10Halfak) a:03Halfak [16:37:44] 10Scoring-platform-team: Article Quality tokenizer error - https://phabricator.wikimedia.org/T256085 (10Halfak) I filed an issue against mwparserfromhell. https://github.com/earwig/mwparserfromhell/issues/248 [16:39:50] 10Scoring-platform-team, 10revscoring, 10artificial-intelligence: Refactor revscoring to handle session-orientation - https://phabricator.wikimedia.org/T231214 (10Halfak) p:05Triage→03Lowest [16:41:14] 10Scoring-platform-team (Current), 10editquality-modeling, 10Spanish-Sites, 10artificial-intelligence: Missing observations from eswikiquote - https://phabricator.wikimedia.org/T254785 (10Halfak) 05Open→03Resolved a:03Halfak Thanks for the information @MarcoAurelio. Given that this is an expected de... [16:42:32] 10Scoring-platform-team, 10revscoring, 10artificial-intelligence: [Spike] Implement script-optimized tokenization - https://phabricator.wikimedia.org/T254356 (10Halfak) @HAKSOAT can you link to your notes? [16:43:48] 10Scoring-platform-team (Current), 10Research, 10drafttopic-modeling: Add wikidata to articletopic pipeline - https://phabricator.wikimedia.org/T254289 (10Halfak) p:05Triage→03High a:03Dibyaaaaax [16:45:14] 10ORES, 10Scoring-platform-team, 10drafttopic-modeling: Experiment with Topic modeling in KubeFlow - https://phabricator.wikimedia.org/T247564 (10Halfak) 05Open→03Declined Declining for now. We're doing a more fundamental exploration of model management frameworks and we might come back to this at some... [16:45:16] 10ORES, 10Scoring-platform-team: [Discuss] Future ORES architecture - https://phabricator.wikimedia.org/T226193 (10Halfak) [16:47:09] 10Scoring-platform-team (Current), 10Discovery-Search, 10Elasticsearch, 10revscoring, 10artificial-intelligence: Improve the performance and quality of tokenization in revscoring - https://phabricator.wikimedia.org/T248480 (10HAKSOAT) I decided to go with the non-cjk lexicon but with the regex for matchi... [16:47:35] 10Scoring-platform-team, 10revscoring, 10artificial-intelligence: [Spike] Implement script-optimized tokenization - https://phabricator.wikimedia.org/T254356 (10HAKSOAT) Discussion can bee found here: https://phabricator.wikimedia.org/T248480 [16:54:09] 10Scoring-platform-team, 10Research: Write Python util for converting Wikidata claims to features for ML models - https://phabricator.wikimedia.org/T252775 (10Dibyaaaaax) There are some Wikidata items that represent Wikipedia pages that aren't articles. Eg. [[ https://www.wikidata.org/wiki/Q8207058 | Q8207058... [17:12:47] 10Scoring-platform-team, 10Research, 10artificial-intelligence: [Epic] Article importance prediction model - https://phabricator.wikimedia.org/T155541 (10Isaac) a:03Isaac I'm going to go ahead and claim this epic task as we're looking to begin work on article importance. I'm going to update the task descri... [17:45:55] 10Scoring-platform-team (Current), 10Operations, 10Release-Engineering-Team: Production shell access for Chris Albon - https://phabricator.wikimedia.org/T256412 (10Nuria) Hello, @calbon cannot ssh to stat1007.eqiad.wmnet , i think tehse changes have not gone in yet. Also user will be needing kerberos creden... [18:36:46] 10Scoring-platform-team, 10Research, 10artificial-intelligence: [Epic] Article importance prediction model - https://phabricator.wikimedia.org/T155541 (10Isaac) [18:47:59] haksoat, I've updated the viwiki vectors in https://analytics.wikimedia.org/published/datasets/archive/public-datasets/all/ores/topic/vectors/ [18:48:14] Would you pull down the 10k vectors for viwiki and give it a try as part of your experimentation? [19:00:23] Okay [19:00:27] I'll do that [19:00:42] Thanks