AI

In deep learning, there are two very different ways to process input (like an image or a document).

We introduce the Dynamic Coattention Network, a state of the art neural network designed to automatically answer questions about documents.

Imagine you were a young child and wanted to ask about something. How would you describe a new object?

The WikiText language modeling dataset is a collection of over 100 million tokens extracted from the set of verified Good and Featured articles on Wikipedia.

We read a lot about how artificial intelligence will change the world: self-driving cars, bots that text like humans, computers that can tell you, without a doubt, what a cat is. While this is interesting, a lingering question is: how will we actually use it? How will AI integrate into our daily

Neural Machine Translation (NMT) systems, introduced only in 2013, have achieved state of the art results in many MT tasks.

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering.

Technology is constantly evolving, and businesses are becoming more and more dependent on technology to run their businesses efficiently. Here are just some of the ways technology has changed business for the better; by streamlining sales techniques and the sales process. Gordon Moore predicted

Today, we published new state of the art results on a variety of natural language processing (NLP) tasks. Our model, which we call the Dynamic Memory Network (DMN), combines two lines of recent work on memory and attention mechanisms in deep learning.