Human language technologies
Researching software and systems that bridge the linguistic divide between people and machines to make communicating with computers as natural as speaking with family and friends.
Video
SysSieve: Extracting Actionable Insights from Unstructured Text
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…
Group
Language and Information Technologies
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…
Project
Deep Learning for Machine Reading Comprehension
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…
Microsoft Research Blog
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
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…
Video
Video Abstract: Customizing Speech Recognition for Higher Accuracy Transcriptions
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…
Publication