News

In a paper accepted to the 2020 NeurIPS conference, Google and Stanford researchers explore the bias exhibited by certain kinds of computer vision algorithms — convolutional neural networks (CNNs) — trained on the open source ImageNet dataset. Unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. Their work indicates that CNNs’ bias toward textures may…

Facebook says it’s using AI to prioritize potentially problematic posts for human moderators to review as it works to more quickly remove content that violates its community guidelines. The social media giant previously leveraged machine learning models to proactively take down low-priority content and left high-priority content reported by users to human reviewers. But Facebook claims it now…

Many real-world problems require complex coordination between multiple agents — e.g., people or algorithms. A machine learning technique called multi-agent reinforcement learning (MARL) has shown success with respect to this, mainly in two-team games like Go, DOTA 2, StarCraft, hide-and-seek, and capture the flag. But the human world is far messier than games. That’s because humans face social…

Entity linking fulfills a key role in grounded language understanding. Given a text mention of an entity (e.g., the word “helpful”), an algorithm identifies the entity’s corresponding entry in a knowledge base (such as a Wikipedia article). To extend its usefulness, researchers at Google propose a new technique where language-specific mentions resolve to a language-agnostic knowledge base.