Monday, September 17, 2018

Hate Speech-Detecting AIs Can Be Fooled: Study

The study found that bad grammar and awkward spelling might make toxic social media comments harder for artificial intelligence (AI) detectors to spot.

from NDTV Gadgets - Latest https://ift.tt/2MDzs3W
at
Labels: ,

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

WhatsApp Reportedly Issues Fix for Chat Syncing Issue With Linked Devices

WhatsApp is reportedly implementing a security fix to address the issue where a user's chats across devices were not synced properly. Th...