Videos

Video Abstract: Machine Reading Comprehension over Automotive Manual

1 month ago
Maluuba’s vision is to build literate machines. The research team has built deep learning models that can process written unstructured text and answer questions against it. The demo will showcase Maluuba’s machine reading comprehension (MRC) system by ingesting a 400-page automotive manual and answering users’ questions about it in real time. The long-term vision for […]

Video Abstract: Interactive Chinese Learning App

1 month ago
When traveling to China it’s best to know at least a bit of the language. The mobile app called Learn Chinese can help travelers enjoy a better journey. Learn Chinese teaches in an interactive way, by using speech and natural language processing technology. The AI robot teacher corrects the user’s Chinese pronunciation and wording through […]

Access and Understanding in the Classroom: How Deaf Children Learn (or not)

1 month ago
Marc Marschark, Ph.D. Center for Education Research Partnerships National Technical Institute for the Deaf – Rochester Institute of Technology For more than 100 years, investigators have taken a keen interest in language and cognition of deaf learners. In many ways, their research has played a central role in arriving at our current understanding of how […]

Rethinking Distributed Systems for the Datacenter

2 months ago
Today’s most popular applications are deployed as massive-scale distributed systems in the datacenter. Keeping data consistent and available despite server failures and concurrent updates is a formidable challenge. Two well-known abstractions, strongly consistent replication and serializable transactions, can free developers from these challenges by transparently masking failures and treating complex updates as atomic units. Yet […]

Life without CONS

2 months ago
Can higher-order functional programs solve more problems than first-order programs? Answer: NO, since both program classes are Turing complete. The reason is that higher-order values can be simulated by first-order values: use function “closures” built by the list constructor “CONS”. Complexity theory characterizes the expressive power of “cons-free” programs with different data orders and control […]

Video Abstract: Bing Visual Search

2 months ago
Visual search, AKA search by image, is a new way of searching for information using an image or part of an image as the query. Similar to text search, which connects keyword queries to knowledge on the web, the ultimate goal of visual search is to connect camera captured data or images to web knowledge. […]

Video Abstract: Zo AI

2 months ago
Zo is a sophisticated machine conversationalist with the personality of a 22-year-old with #friendgoals. She hangs out on Kik and Facebook and is always interested in a casual conversation with her growing crowd of human friends. Zo is an open-domain chatbot and her breadth of knowledge is vast. She can chime into a conversation with […]

A Generic Framework for Mining Top-k Representative Subgraph Patterns

2 months ago
Mining subgraph patterns is an active area of research. Till now, the focus has primarily been on mining all subgraph patterns in the given database. However, due to the exponential subgraph search space, the number of patterns mined, typically, is too large for any human mediated analysis. Consequently, deriving insights from the mined patterns is […]

Video Abstract: InstaFact—Bringing Knowledge to Office Apps

2 months ago
This demo shows how InstaFact brings the information and intelligence of the Satori knowledge graph into Microsoft’s productivity software. InstaFact can automatically complete factual information in the text a user is writing or can verify the accuracy of facts in text. It can infer the user’s needs based on data correlations and simple natural-language clues. […]

Video Abstract: Custom Vision Service

2 months ago
This demo shows how Custom Vision Service can be applied to many AI vision applications. For example, if a client needs to build a custom image classifier, they can submit a few images of objects, and a model is deployed at the touch of a button. Microsoft Office is also using Custom Vision Service to […]

Video Abstract: Private AI

2 months ago
As the volume of data goes up, the quality of machine learning models, predictions, and services will improve. Once models are trained, predictive cloud services can be built on them, but users who want to take advantage of the services have serious privacy concerns about exposing consumer and enterprise data—such as private health or financial […]

Provably Correct Peephole Optimizations with Alive (PLDI ’15)

2 months ago
Video abstract for PLDI 2015 paper. Produced by Neeltje Berger and Natalya Butterworth (Microsoft Research).