Nicolas Angelard-Gontier

Teaching Machines to Learn



I am a Master student affiliated with the MILA insitute and the Reasoning and Learning Lab at McGill University, Montreal, Canada. Supervised by Joelle Pineau, my research focuses on dialogue systems. I am especially interested in generative models as well as their automated evaluation. My favorite tools to study these questions are deep learning and reinforcement learning.

I'm also concerned about other topics such as AI Ethics, theoretical physics, AI in medicine, neuroscience, computational biology, software development, mobile apps development, computer security, and anything that is related to multimedia (3D animations, movie making, music).

I obtained a bachelor of science (B.Sc.) in Computer Science from McGill University in 2016. I accompanied my Computer Science major with a minor in Economics. In between my semesters I did multiple internships. Most notably I worked as a Software Developer Intern from January to August 2016, and as a NLU researcher intern from May to August 2017 at Nuance Communications Inc.

For more details, please find my CV here.


  • "Ethical Challenges in Data-Driven Dialogue Systems"; Peter Henderson, Koustuv Sinha, Nicolas Angelard-Gontier, Nan Rosemary Ke, Genevieve Fried, Ryan Lowe, Joelle Pineau; AAAI/ACM 2017 ; [paper] [slides] [poster] [website] [code]
  • "Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses"; Ryan Lowe, Michael Noseworthy, Iulian Serban, Nicolas Angelard-Gontier, Yoshua Bengio, Joelle Pineau; ACL 2017 (Outstanding Paper Award); [paper]


  • Caption to Image ; Nicolas Angelard-Gontier, Joshua Romoff, Prasanna Parthasarathi; 11-12/2017; [report] [slides] [code]
  • RLLChatBot ; NIPS Conversational Intelligence Challenge; Nicolas Angelard-Gontier, Koustuv Sinha, Peter Henderson, Prasanna Parthasarathi, and Michael Noseworthy; 05/2017 - 12/2017; [poster] [code]
  • Ubuntu Dialogue Corpus with HRED and attention ; Nuance Communications Summer Internship ; 05-09/2017; [report] [poster]
  • "Training a Discriminator to Compare Generative Dialogue Models"; Nicolas Angelard-Gontier; 2017; [report] [slides] [code]
  • "Policy Gradient Methods for Dialogue Response Generation"; Michael Noseworthy, Nicolas Angelard-Gontier; 2017; [report] [slides]
  • "Sentiment Analysis on Movie Reviews"; Nicolas Angelard-Gontier; 2016; [report] [slides] [code]

Previous projects (not related to Machine Learning) can be found in the archive page.