Illustration of two translators on a scale
Machine Learning Research

Choosing Words Carefully: NLP for Translation Chooses the Right Synonym

The words “big” and “large” have similar meanings, but they aren’t always interchangeable: You wouldn’t refer to an older, male sibling as your “large brother” (unless you meant to be cheeky). Choosing among words with similar meanings is critical in language tasks like translation.
Illustration of a doctor and a nurse
Machine Learning Research

Gender Bender

AI learns human biases: In word vector space, “man is to computer programmer as woman is to homemaker,” as one paper put it. New research helps language models unlearn such prejudices.
Talking bubbles inside talking bubbles
Machine Learning Research

Bigger is Better

Natural language processing lately has come to resemble an arms race, as the big AI companies build models that encompass ever larger numbers of parameters. Microsoft recently held the record — but not for long.
Illustration of two people talking with a typo
Machine Learning Research

Found in Translation

Language models can’t correct your misspellings or suggest the next word in a text without knowing what language you’re using. For instance, if you type “tac-,” are you aiming for “taco,” a hand-held meal in Spanish, or “taca,” a crown in Turkish?
Graphs and data related to Plan2Vec
Machine Learning Research

Visual Strategies for RL

Reinforcement learning can beat humans at video games, but humans are better at coming up with strategies to master more complex tasks. New work enables neural networks to connect the dots.
Data and graphs related to a method that synthesizes extracted features of underrepresented classes
Machine Learning Research

Augmentation for Features

In any training dataset, some classes may have relatively few examples. A new technique can improve a trained model’s performance on such underrepresented classes. Researchers introduced a method that synthesizes extracted features of underrepresented classes.
Data and information related to shortcut learning
Machine Learning Research

When Models Take Shortcuts

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.
Data related to YOLOv4
Machine Learning Research

Another Look at YOLO

The latest update of the acclaimed real-time object detector You Only Look Once is more accurate than ever. Researchers at Taiwan’s Institute of Information Science Academia Sinica offer YOLOv4 — the first version not to include the architecture’s original creators.
Generative BST example and graph
Machine Learning Research

Big Bot Makes Small Talk

Facebook recently rolled out its entry in the World’s Biggest Chatbot sweepstakes. In keeping with the company’s social-networking dominance, the bot is designed to excel at chitchat on any subject.
A chatbot called Meena and a graph comparing it with other chatbot services
Machine Learning Research

Toward Open-Domain Chatbots: Meena Scores High on System for Grading NLP Chatbots

Progress in language models is spawning a new breed of chatbots and, unlike their narrow-domain forebears, they have the gift of gab. Recent research tests the limits of conversational AI.
Data related to few-shot learning
Machine Learning Research

Small Data the Simple Way

Few-shot learning seeks to build models that adapt to novel tasks based on small numbers of training examples. This sort of learning typically involves complicated techniques, but researchers achieved state-of-the-art results using a simpler approach.
Information and examples of CheXbert, a network that labels chest X-rays
Machine Learning Research

Human-Level X-Ray Diagnosis

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.
Data and graphs related to teacher networks
Machine Learning Research

Flexible Teachers, Smarter Students

Human teachers can teach more effectively by adjusting their methods in response to student feedback. It turns out that teacher networks can do the same.
Brains and neural signals reading
Machine Learning Research

Listening to the Brain

AI has added an unlikely language to its catalog of translation capabilities: brain waves. Joseph Makin led a group from the University of California San Francisco to render a person’s neural signals as English text while the person while the person read a sentence aloud.
Examples of recognition of real and fake images
Machine Learning Research

Fake Detector

AI’s ability to produce synthetic pictures that fool humans into believing they’re real has spurred a race to build neural networks that can tell the difference. Recent research achieved encouraging results.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox