Featured Demos

The Computer Vision Explorer lets you try and compare a variety of popular computer vision models related to recognition, vision and language, human-centric vision, and scene geometry tasks. Use our example images or try with your own.

The AllenNLP Interpret toolkit makes it easy to apply gradient-based saliency maps and adversarial attacks to new models, as well as develop new interpretation methods. AllenNLP Interpret contains three components: a suite of interpretation techniques applicable to most models, APIs for developing new interpretation methods (e.g., APIs to obtain input gradients), and reusable front-end components for visualizing the interpretation results.

SUPP.AI automatically extracts evidence of supplement and drug interactions from the scientific literature. Search for all known potential interactions with a particular agent, or look up the evidence for a specific interaction.

CrowdSense is an interactive effort to better understand what types of questions people consider to be common sense.

Online disinformation, or fake news intended to deceive, has emerged as a major societal problem. Currently, fake news articles are written by humans, but recently-introduced AI technology based on neural networks might enable adversaries to generate fake news. Our goal is to reliably detect this “neural fake news” so that its harm can be minimized.

Explore ATOMIC, an atlas of everyday commonsense reasoning focused on inferential knowledge, organized through 877k textual if-then descriptions. Then see ATOMIC in action via COMeT, a knowledge base construction engine that learns to access commonsense knowledge implicitly acquired when reading billions of words of text, producing new nodes and connections in commonsense knowledge graphs.

Semantic Sanity Preserver is an adaptive ArXiv feed inspired by ArXiv Sanity. This feed uses an AI model that quickly learns what papers you care about reading and recommends the latest ArXiv research to help you stay up to date on new publications in the field of computer science.

Iconary showcases the world’s first AI system capable of playing a Pictionary-style drawing and guessing game together with a human partner. Team up with the AllenAI artificial intelligence to either draw or guess a set of unique phrases using a limited set of icons to compose your drawing. AllenAI combines advanced computer vision, language understanding, and common sense reasoning to make guesses based on your drawings and to produce its own complex scenes for you to try to guess.

AllenNLP is an open source NLP research library that makes it easy for researchers to design and evaluate new deep learning models for nearly any NLP problem, and makes state-of-the-art implementations of several important NLP models and tools readily available for researchers to use and build upon.