[Spike] Investigate using two set of bad words instead of one
Closed, ResolvedPublic
Actions

Assigned To

Authored By

	Ladsgroup
	Jul 10 2015, 5:25 PM

Description

Currently we have one set of bad words.
But it would be better to have two set of bad words, one for swearwords (it shouldn't be used anywhere) and one for non-encyclopedic word (it can be used out of main namespace). Let us compare result of predictions between those two classifiers and then to use it or not.

Event Timeline

Ladsgroup created this task.Jul 10 2015, 5:25 PM

Ladsgroup claimed this task.

Ladsgroup raised the priority of this task from to Needs Triage.

Ladsgroup updated the task description. (Show Details)

Ladsgroup added a project: Machine-Learning-Team (Active Tasks).

Ladsgroup added subscribers: Ladsgroup, Halfak.

Restricted Application added a subscriber: Aklapper. · View Herald TranscriptJul 10 2015, 5:25 PM

Ladsgroup reassigned this task from Ladsgroup to Halfak.Sep 2 2015, 2:05 PM

Ladsgroup set Security to None.

Ladsgroup moved this task from Parked to Backlog on the Machine-Learning-Team (Active Tasks) board.

Halfak moved this task from Backlog to Paused on the Machine-Learning-Team (Active Tasks) board.Sep 11 2015, 4:31 PM

Heh. This was done so long ago, I don't even know what to say.

Halfak closed this task as Resolved.Mar 14 2016, 3:42 PM

[Spike] Investigate using two set of bad words instead of oneClosed, ResolvedPublicActions

Description

Event Timeline

[Spike] Investigate using two set of bad words instead of one
Closed, ResolvedPublic
Actions