FigureQA Dataset
Answering questions about a given image is a difficult task, requiring both an understanding of the image and the accompanying query. Microsoft Montreal’s FigureQA dataset introduces a new visual reasoning task for research, specific to…
Frames Dataset
Frames is a dataset designed to encourage research towards conversational agents which can support decision-making in complex settings, in this case – booking a vacation including flights and a hotel. More than just searching a…
NewsQA Dataset
The purpose of Microsoft Montreal’s NewsQA dataset is to help the research community build algorithms that are capable of answering questions requiring human-level comprehension and reasoning skills. Leveraging CNN articles from the DeepMind Q&A Dataset,…
A Reductions Approach to Fair Classification
Designing Gaze Visualizations for Remote Collaboration and Learning
Technological advances are improving our ability to work and learn together, even when separated by distance. However, distributed environments lack many of the rich interpersonal cues that we take for granted in co-located collaboration. For…
Design and Evaluation of Effective, Interactive, and Interpretable Machine Learning
Machine learning is ubiquitous in domains such as criminal justice, credit, lending, and medicine. Traditionally, these models are evaluated based on their predictive performance on held-out data sets. However, to convince non-expert users that these…
The Four Big Bets (Illustrated via a Journey in Program Synthesis)
Sumit Gulwani will talk about the four bets that he made in the second half of his research career, which yielded greater personal satisfaction. He will illustrate this in the context of his research agenda…