Faculty Summit 2019 | The future of work
This year marks the 20th anniversary of the Microsoft Research Faculty Summit held in Redmond at the Microsoft Conference Center, July 17-18, 2019. The Faculty Summit brings together the intellectual power of researchers from across…
InterpretML
InterpretML is an open-source python package for training interpretable models and explaining blackbox systems. Historically, the most intelligible models were not very accurate, and the most accurate models were not intelligible. Microsoft Research has developed…
Multi-Task Deep Neural Networks for Natural Language Understanding (MT-DNN)
Multi-task learning toolkit for natural language understanding, including knowledge distillation.
ConvLab
ConvLab is an open-source multi-domain end-to-end dialog system platform, aiming to enable researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to…
Decentralized & Collaborative AI on Blockchain
Verifying Web Page Layouts
Web pages define their appearance using Cascading Style Sheets. However, the CSS language’s quirks and subtleties make it difficult for designers to write, debug, and test CSS to implement their designs. Understanding all the ways…
Diverse Counterfactual Explanations (DiCE) for ML
DiCE is a Python library to explain an ML model such that the explanation is truthful to the model and yet interpretable to people. This connects to the “Explainable AI systems” theme.