Have wondered about this and now we know:

Facebook’s artificial intelligence-powered content moderators can’t read some languages used on the platform, raising concerns about how the company is policing content in countries that speak languages other than English, The Wall Street Journal reported Thursday.

Source: Facebook’s AI Moderators Can’t Read All Languages Online: WSJ

It is mostly impossible for humans to make accurate and effective content moderation decisions; it is even tougher for algorithms to do that automatically. The problem is that all user generated content services will eventually have content that someone else finds objectionable. There does not seem to be any effective solution to this problem.