News and Awards

Microsoft Research Montreal lab last week announced an open-source project called TextWorld. TextWorld is an extensible framework based on Python which can be used for generating text-based games. Researchers can use this framework to train…

New research focuses on the challenges of machine learning biases, and provides a provably and empirically sound method for turning any common classifier into a ‘fair’ classifier according to any of a wide range of…

While the rest of the Microsoft world squeaked with excitement about new hardware and free collaboration tools, the boffins at Redmond’s Montréal Research Lab have looked to history as way to help Reinforcement Learning (RL)…

TextWorld enables researchers to define how games should play out by providing high-level specifications. It also lets researchers use existing, human-written games to create an even more challenging training environment.

The Big Data Hubs are a National Science Foundation-sponsored effort that supplies cloud computing credits to large scientific projects, including Azure credits donated by Microsoft.

Best Short Paper Award for “Cross Domain Regularization for Neural Ranking Models Using Adversarial Learning” with Daniel Cohen, Katja Hofmann, and W. Bruce Croft, SIGIR 2018.