Human language technologies
Advancing how machines understand and generate human language across speech, text, and translation.
Hope Speech and Help Speech: Surfacing Positivity Amidst Hate
Tackling online attacks targeting certain individuals, groups of people, or communities is a major modern-day web challenge. Research efforts in hate speech detection thus far have largely focused on identifying and subsequently filtering out negative…
PROSE Framework
Microsoft PROSE SDK is a framework of technologies for programming by examples: automatic generation of programs from input-output examples.
Project EPOCh: Extending Patient Outreach with Chat
Patient-centred care and good communication between patients and healthcare providers has been shown to improve medical adherence. However, it is costly and difficult to provide, especially in Global Health settings where patient volumes are high…
MIcrosoft News Dataset (MIND)
MIcrosoft News Dataset (MIND) is a large-scale dataset for news recommendation research. It was collected from anonymized behavior logs of Microsoft News website. The mission of MIND is to serve as a benchmark dataset for…
Trustworthy AI
In recent times, the explosion of information from a variety of sources and cutting edge techniques such as Deepfake have made it increasingly important to check the credibility and reliability of the data. Large volumes…
Learning with Weak Supervision
The need for labeled data is one of the largest bottlenecks in training supervised learning models like deep neural networks. This is especially the case for many real-world tasks where large scale annotated examples are…
Few-shot Learning
Deep neural networks including pre-trained language models like BERT, Turing-NLG and GPT-3 require thousands of labeled training examples to obtain state-of-the-art performance for downstream tasks and applications. Such large number of labeled examples are difficult…
Knowledge Distillation
Modern machine learning applications have enjoyed a great boost utilizing deep and large neural network models, allowing them to achieve state-of-the-art results on a wide range of tasks such as question-answering, conversational AI, search and…