Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
Maluuba Supports and Encourages Diversity in Deep Learning Research
In this new work, we perform an empirical study to explore the relevance of unsupervised metrics for the evaluation of goal-oriented Natural Language Generation.
Maluuba Celebrates New Office Opening
Learn about our work with McGill's AI for Good and the Women in Deep Learning events this month in Montreal
Hybrid Reward Architecture (HRA) Achieving super-human performance on Ms. Pac-Man
Celebrating the opening of our new Montreal office.
A Joint Model for Question Answering and Question Generation
We propose a new technique, called Hybrid Reward Architecture, that let us achieve the maximum possible score of 999,990 points in the game Ms. Pac Man.
Maluuba at RLDM in Ann Arbor
Our latest effort in QA research involves teaching machines to jointly ask and answer questions.
Maluuba proud to partner with McGill's AI For Social Good Summer Lab
Maluuba will be attending the 2017 Multi-disciplinary Conference on Reinforcement Learning and Decision Making, taking place June 11 - 14 in Ann Arbor, Michigan.
Maluuba workshop at the AI Forum at C2 Montreal
Maluuba is proud to be participating in the AI for Social Good Summer Lab, taking place at McGill University this June.
Advancing machine comprehension with question generation
Maluuba Research Manager Adam Trischler has joined the line up of speakers at The AI Forum. He'll deliver a workshop on machine comprehension in enterprise.
Teaching systems to read, answer and even ask questions
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. To our knowledge, this is the first end-to-end, text-to-text model for question generation
learn more about Maluuba's work with Microsoft to drive breakthroughs in machine reading comprehension.