Jigsaw Multilingual Toxic Comment Classification

It only can take just one toxic remark to bitter an on the web discussion. The Conversation AI workforce, a exploration initiative started by Jigsaw and Google, builds technologies to defend voices in the conversation. A main space of target is device studying products that can establish toxicity in on the web discussions, where by toxicity is described as anything rude, disrespectful, or normally very likely to make someone leave a discussion. If these toxic contributions can be determined, we could have a safer, extra collaborative web.

Picture credit score: US Office of Defense/Wikipedia/Public Domain

Jigsaw’s API, Perspective, serves toxicity products, and others in a growing established of languages. Around the past year, the area has observed extraordinary multilingual abilities from the latest model innovations, which include couple of- and zero-shot studying.

Submission to this Problem must be acquired by eleven:59 PM UTC, June fifteen, 2020.

Source: Kaggle