Human language technologies
Advancing how machines understand and generate human language across speech, text, and translation.
Multilingual Model Transfer
In this project we develop new deep learning models for bootstrapping language understanding models for languages with no labeled data using labeled data from other languages.
MASS: Masked Sequence to Sequence Pre-training for Language Generation
MASS is a novel pre-training method for sequence to sequence based language generation tasks. It randomly masks a sentence fragment in the encoder, and then predicts it in the decoder.
Phonetic matching library
A phonetic matching library. Includes text utilities to do string comparisons on phonemes (the sound of the string), as opposed to characters.
Calendar.help: A Virtual Meeting Scheduling Assistant
Scheduling meetings is tedious. It gets even more challenging when people use different calendaring systems or meet across different time zones. People need to have multiple dialogues to find an optimal time for them to…
Microsoft Teams: Collaborate with Any Researcher Anywhere
See how researchers from the Heart Research Institute collaborate in real-time on documents, meet online and chat with confidence their intellectual property is protected using Microsoft Teams. Save your grant funding because Microsoft Teams is…
Microsoft Whiteboard: Digital, Freeform Canvas for Creative Collaboration
We are seeing a shift in the way people work and collaborate across spaces and locations. Designed for modern workplaces, Microsoft Whiteboard is a freeform intelligent canvas where teams can brainstorm, plan, and iterate. It…
VERSE: Voice. Exploration. Retrieval. Search.
People with visual impairments are expert users of audio interfaces, including voice-activated virtual assistants and screen readers. Through interviews and surveys of this population, we learned that virtual assistants are convenient and accessible, but lack…
