Teaching machines to ask questions
In addition to our work in training machines to read and reason upon text to answer questions, we have been exploring ways to to train machines to ask questions.
In our latest paper, we propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers.
Frames dataset released
Maluuba's Frames dataset is designed to help drive research that enables truly conversational agents that can support decision-making in complex settings. Prepared through human-to-human conversations, the dataset contains complex, natural dialogues with users considering different options, comparing packages, and progressively building rich descriptions through conversation.
News and updates
the next challenges for reinforcement learning research
14 Mar 2017
We explore some of the remaining challenges in the field of reinforcement learning.
Towards Artificial General Intelligence: Creating curious machines
10 Jan 2017
Teaching artificial agents to accomplish tasks through efficient information-seeking behaviour.
memory and machines: a milestone study in goal-oriented dialogue systems
21 Dec 2016
Access our paper and Frames, our new dataset for goal-oriented dialogue research.
Dedicated to tackling big challenges in language understanding and artificial intelligence
With a focus on deep learning and reinforcement learning, our growing team of renowned experts is working closely with industry and academia. Now, as part of Microsoft, Maluuba is accelerating our approach to drive breakthroughs in AI research and application. Learn more about our vision, access our academic publications and interact with our public datasets.
At Maluuba, we believe that language understanding is inextricable from solving Artificial Intelligence.
Our goal is to teach machines to model human-like reasoning and the decision making capabilities of the brain.