Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Publication
Domain-Adaptive Neural Automated Essay Scoring.
Outil
GLUECoS
This is the repo for the ACL 2020 paper GLUECoS: An Evaluation Benchmark for Code-Switched NLP GLUECoS is a benchmark comprising of multiple code-mixed tasks across 2 language pairs (En-Es and En-Hi)
Projet
DeepSpeed
DeepSpeed, part of the Microsoft AI at Scale initiative, is a deep learning optimization library that makes distributed training easy, efficient, and effective.
Vidéo
Frontiers in Machine Learning: Climate Impact of Machine Learning
Microsoft has made an ambitious commitment to remove its carbon footprint in response to the overwhelming urgency of addressing climate change. Meanwhile, recent advances in machine learning (ML) models, such as transformer-based NLP, have produced…
Vidéo
Frontiers in Machine Learning: Learning from Limited Labeled Data: Challenges and Opportunities for NLP
Modern machine learning applications have enjoyed a great boost utilizing neural networks models, allowing them to achieve state-of-the-art results on a wide range of tasks. Such models, however, require large amounts of annotated data for…
Vidéo
Frontiers in Machine Learning: Saving Lives with Interpretable ML
This session is about Saving Lives Using Interpretable Machine Learning in HealthCare. It’s critical to make sure healthcare models are safe to deploy. One challenge is that most patients are receiving treatment and that affects…
Vidéo
Frontiers in Machine Learning: Machine Learning Reliability and Robustness
As Machine Learning (ML) systems are increasingly becoming part of user-facing applications, their reliability and robustness are key to building and maintaining trust with users and customers, especially for high-stake domains. While advances in learning…
Vidéo
Frontiers in Machine Learning: Big Ideas in Causality and Machine Learning
Causal relationships are stable across distribution shifts. Models based on causal knowledge have the potential to generalize to unseen domains and offer counterfactual predictions: how do outcomes change if a certain feature is changed in…
