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.
Tool
UniLM – Unified Language Model Pre-training
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities.
GitHub Publication Publication Publication Publication Publication
Video
Visually Grounded Language Understanding and Generation
In this talk, I will present our latest work on comprehending and generating visually grounded language. First, we will discuss the challenging task of learning visual grounding of language. I will introduce how to pretrain…
Video
Learning to Map Natural Language to General Purpose Source Code
Models that map natural language (NL) to source code in general purpose languages such as Java, Python, and SQL find utility amongst two main audiences viz. developers who can manipulate the generated code, and non-expert…
Microsoft Research Blog
Layer Trajectory BLSTM: New evolution enhances speech recognition technology
Speech is a signal that can enable natural interaction between human and machine. In order to facilitate this exchange, machines have to be able to recognize what a human has spoken, both the words and…
Event
Microsoft at Interspeech 2019
Interspeech is the world‘s largest and most comprehensive conference on the science and technology of spoken language processing. Microsoft joins the conference as a proud gold sponsor. Stop by our booth to chat with our…
Microsoft Research Blog
Bring your phones to the conference table: creating ad hoc microphone arrays from personal devices
Recent advances in machine learning and signal processing, as well as the availability of massive computing power, have resulted in dramatic and steady improvement in speech recognition accuracy. Voice interfaces to digital devices have become…
