We've updated our Privacy Policy to make it clearer how we use your personal data.

We use cookies to provide you with a better experience, read our Cookie Policy

Advertisement

Hate Speech Detecting-AIs Tricked by Typos

News   Sep 17, 2018 | Original Press Release from Aalto University

 
Hate Speech Detecting-AIs Tricked by Typos

How Google Perspective rates a comment otherwise deemed toxic after some inserted typos and a little love. Credit: Aalto University

 
 
Advertisement
 

RELATED ARTICLES

Modeling Meat Could Improve Quality and Reduce Waste

News

By treating meat as a network of flexible polymers surrounded by flowing moisture, computer models can accurately predict how much it will shrink when cooked.

READ MORE

App Concept Could Track Coronavirus Without Needing to Know Your Location

News

A team of medical researchers and bioethicists at Oxford University has published results today in Science that furthers our understanding of coronavirus transmission. The researcher could assist the development of mobile apps for instant contact tracing in record time.

READ MORE

AI Analysis Could Accelerate Stroke Detection

News

A new study showcases the potential of artificial intelligence (AI) for analyzing brain images during stroke. The process of lesion segmentation normally involves manual analysis by expert radiologists, but new techniques could speed up the analysis.

READ MORE

 

To personalize the content you see on Technology Networks homepage, Log In or Subscribe for Free

LOGIN SUBSCRIBE FOR FREE