Research
Advancing how machines understand and generate human language across speech, text, and translation.
From ferry schedules to dinner reservations, Cortana is the digital assistant designed to help people get things done. Cortana will eventually be everywhere people need assistance—on the phone, PC, Xbox One, and other places like…
By Eric Horvitz, Technical Fellow and Managing Director, Microsoft We’re at an inflection point for AI technologies. Rising capabilities and possibilities have been catalyzed by jumps in the availability of data and computational power. Increasing…
Content is key for online industry. With the growing adoption of AI among various businesses, we are exploring ways that AI can help organize and create content in different forms, including text, audio, image, video etc.…
Understanding free-form text is hard, be it bug reports or trouble tickets written by engineers or feedback/complaints from customers. We have built SysSieve, a learning system to do automated analysis of these important unstructured (yet…
The Language and Information Technologies group harnesses AI to understand how people interact with information systems and develop new experiences to empower people to be more productive. Our research interests are at the intersection of information…
The goal of this project is to teach a computer to read and answer general questions pertaining to a document. We recently released a large scale MRC dataset, MS MARCO. We developed a ReasoNet model…
The vision of the researchers at the Microsoft Research Montreal lab is to create machines that can comprehend, reason and communicate with humans. As part of this vision, our dialogue team has been doing research…
Two of the most important components of speech recognition systems are the acoustic model and the language model. Those models behind Microsoft’s speech recognition engine have been optimized for certain usage scenarios, such as interacting…
