Math equations represented as trees
Language

Neural Networks Study Math

In tasks that involve generating natural language, neural networks often map an input sequence of words to an output sequence of words. Facebook researchers used a similar technique on sequences of mathematical symbols, training a model to map math problems to math solutions.
2 min read
Single Headed Attention RNN (SHA-RNN)
Language

Language Modeling on One GPU

The latest large, pretrained language models rely on trendy layers based on transformer networks. New research shows that these newfangled layers may not be necessary.
2 min read
Richard Socher
Language

Richard Socher: Boiling the Information Ocean

Ignorance is a choice in the Internet age. Virtually all of human knowledge is available for the cost of typing a few words into a search box.
2 min read
Yann LeCun
Language

Yann LeCun: Learning From Observation

How is it that many people learn to drive a car fairly safely in 20 hours of practice, while current imitation learning algorithms take hundreds of thousands of hours, and reinforcement learning algorithms take millions of hours? Clearly we’re missing something big.
2 min read
Illustration of a fireplace with "Happy holidays" cards in English, Spanish and French
Language

Language Models Get Literate

Earlier language models powered by Word2Vec and GloVe embeddings yielded confused chatbots, grammar tools with middle-school reading comprehension, and not-half-bad translations. The latest generation is so good, some people consider it dangerous.
2 min read
Sesame Street characters together
Language

Inside AI’s Muppet Empire

As language models show increasing power, a parallel trend has received less notice: The vogue for naming models after characters in the children’s TV show Sesame Street.
1 min read
Automatically generated text summary
Language

Keeping the Facts Straight

Automatically generated text summaries are becoming common in search engines and news websites. But existing summarizers often mix up facts. For instance, a victim’s name might get switched for the perpetrator’s.
2 min read
Information about a model for multi-document summarization and question answering
Language

Bigger Corpora, Better Answers

Models that summarize documents and answer questions work pretty well with limited source material, but they can slip into incoherence when they draw from a sizeable corpus. Recent work addresses this problem.
2 min read
Word vectors
Language

Finer Tuning

A word-embedding model typically learns vector representations from a large, general-purpose corpus like Google News. But to make the resulting vectors useful in a specialized domain, they must be fine-tuned on a smaller, domain-specific dataset. Researchers offer a more accurate method.
2 min read
Booksby.ai book covers created by AI
Language

Who’s Minding the Store?

Amazon, watch your back. There’s a new player in the book business and, unlike Jeff Bezos, it doesn’t need eight hours of sleep a night. The online bookstore Booksby.ai is run entirely by AI. Neural networks write the books, create the cover art, price the merchandise, even write the reviews.
1 min read
Illustration of vending machine with candy and the text "Say "trick or treat""
Language

Machines Take Everyone’s Job

From blue collar laborers to lab coated professionals, is any job safe from AI? AI will exceed human performance at a wide range of activities. Huge populations will become jobless.
2 min read
Process of labeling doctors' notes
Language

Cracking Open Doctors’ Notes

Weak supervision is the practice of assigning likely labels to unlabeled data using a variety of simple labeling functions. Then supervised methods can be used on top of the now-labeled data.
2 min read
Map of Northamerica showing different indigenous languages by location
Language

Power of Babel

More than 900 indigenous languages are spoken across the Americas, nearly half of all tongues in use worldwide. A website tracks the growing number of resources available for natural language processing researchers interested in studying, learning from, and saving these fading languages.
1 min read
Proposed model for abstractive summarization of a scientific article
Language

Two Steps to Better Summaries

Summarizing a document using original words is a longstanding problem for natural language processing. Researchers recently took a step toward human-level performance in this task, known as abstractive summarization, as opposed to extractive summarization.
1 min read
Chart with number of AI startup acquisitions from 2010 to 2019
Language

AI Startups in Demand

AI startups are being scooped up at an accelerating pace, many by companies outside the tech sphere. A report by CB Insights shows that, as of August, 2019 was on track to surpass last year’s record number of AI startup acquisitions.
1 min read

Subscribe to The Batch

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