Research Tools: code, datasets, & models

The Quantum Development Kit includes Q#, a brand-new quantum-focused programming language with native type, operators, and other abstraction, advanced code optimization in a simulated environment and a collection of ready-to-use open source libraries and samples…

The NL2API dataset includes the web APIs call from the Microsoft Graph API suite, which are respectively used to search a user’s emails and calendar events. Each data points include the API call, its canonical…

Visual Navigation via Language-based Assistance

A set of Databricks and Azure notebook scripts that compute urban heat island effects for all major cities in the United States. Daily indices for each city are computed from January 1, 2008 to present…

This PyTorch package implements the Multi-Task Deep Neural Networks (MT-DNN) for Natural Language Understanding.

We introduce a new corpus of descriptions of Xbox avatars created by actual gamers. Each avatar is specified by 19 attributes, including clothing and body type, allowing for more than 10^20 possibilities. Using Amazon Mechanical…

Building a computer system to automatically solve math word problems written in natural language. SigmaDolphin is a project initiated in early 2013 at Microsoft Research Asia, with the primary goal of building a computer intelligent…

Microsoft TV White Spaces database enables secondary users the ability to use the TV White Spaces spectrum in order to provide for overall spectrum utilization. The design document outlines the technical implementation of the webservices…

Deep4Cast is a scalable machine learning package implemented in Python. It has a front-end API designed to be similar to scikit-learn, but is based on Keras. It was designed for medium to large size time…

OpenPAI is an open source platform that provides complete AI model training and resource management capabilities, it is easy to extend and supports on-premise, cloud and hybrid environments in various scale.