Portrait of Laurent Charlin

Laurent Charlin

Core Academic Member
lcharlin@mila.quebec
Canada CIFAR AI Chair
Associate Professor, HEC Montréal, Department of Decision Sciences
Associate Professor, Université de Montréal, Department of Computer Science and Operations Research
Research Topics
AI for Science
Data Mining
Deep Learning
Generative Models
Graph Neural Networks
Information Retrieval
Natural Language Processing
Probabilistic Models
Recommender Systems
Reinforcement Learning
Representation Learning
Google Scholar
LinkedIn
X

Biography

Laurent Charlin is a Canada CIFAR AI Chair at Mila and an associate professor at HEC, the business school affiliated with the University de Montréal. He is also a core member of Mila—Quebec Institute for Artificial Intelligence.

Charlin’s research focuses on developing novel machine learning models to aid in decision-making. Recent work has focused on learning from data that changes over time, and on applications in fields such as recommender systems and optimization.

He has a number of highly cited publications on dialogue systems (chatbots). He co-developed the Toronto Paper Matching System (TPMS), which has been widely used by computer science conferences for matching reviewers to papers. He has also given MOOCs, introductory talks and media interviews to contribute to knowledge transfer and improve AI literacy.

Current Students

Neda Adl
Master's Research - HEC Montréal
Neda@mila.quebec
Anirudh Buvanesh
PhD - Université de Montréal
Co-supervisor :
Aaron Courville
anirudb1102@gmail.com
Github
Félix Gauthier
Master's Research - HEC Montréal
felix.gauthier@mila.quebec
Soraya Ghassemlou
Master's Research - McGill University
soraya.ghassemlou@mila.quebec
Website
Github
Nicolas Goulet
PhD - HEC Montréal
Principal supervisor :
Eva Portelance
nicolas.goulet@mila.quebec
Google Scholar
Shubham Gupta
PhD - Université Laval
Principal supervisor :
Cem Subakan
shubham.gupta@mila.quebec
Ben Hudson
PhD - Université de Montréal
Co-supervisor :
Emma Frejinger
ben.hudson@mila.quebec
Website
Github
Google Scholar
Mizu Nishikawa-Toomey
PhD - Université de Montréal
Co-supervisor :
Dhanya Sridhar
mizu.nishikawa-toomey@mila.quebec
Website
Github
Google Scholar
Fırat Öncel
PhD - Concordia University
Principal supervisor :
Mirco Ravanelli
firat.oncel@mila.quebec
Website
Github
Google Scholar
Oleksiy Ostapenko
Collaborating Alumni - Université de Montréal
ostapeno@mila.quebec
Google Scholar
Emiliano Penaloza
PhD - Université de Montréal
emiliano.penaloza@mila.quebec
Website
Github
Gaurav Sahu
Postdoctorate - HEC Montréal
Co-supervisor :
Chris Pal
gaurav.sahu@mila.quebec
Website
Github
Google Scholar
Omar Salemohamed
PhD - Université de Montréal
omar.salemohamed@mila.quebec
Yipeng Zhang
PhD - Université de Montréal
yipeng.zhang@mila.quebec
Google Scholar

Publications

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Iulian V. Serban
Alessandro Sordoni
Ryan Lowe
Laurent Charlin
Joelle Pineau
Aaron Courville
Yoshua Bengio
Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterance… (see more)s in a dialogue. In an effort to model this kind of generative process, we propose a neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with recent neural network architectures. We evaluate the model performance through automatic evaluation metrics and by carrying out a human evaluation. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate the generation of long outputs and maintain the context.
2017-02-11
Proceedings of the AAAI Conference on Artificial Intelligence (published)
doi.org
arxiv.org
Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus
Ryan Lowe
Nissan Pow
Iulian Vlad Serban
Laurent Charlin
Chia-Wei Liu
Joelle Pineau
In this paper, we construct and train end-to-end neural network-based dialogue systems usingan updated version of the recent Ubuntu Dialogue… (see more) Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This dataset is interesting because of its size, long context lengths, and technical nature; thus, it can be used to train large models directly from data with minimal feature engineering, which can be both time consuming and expensive. We provide baselines  in two different environments: one where models are trained to maximize the log-likelihood of a generated utterance  conditioned on the context of the conversation, and one where models are trained to select the correct next response from a list of candidate responses. These are both evaluated on a recall task that we call Next Utterance Classification (NUC), as well as other generation-specific metrics. Finally, we provide a qualitative error analysis to help determine the most promising directions for future research on the Ubuntu  Dialogue Corpus, and for end-to-end dialogue systems in general.
2017-01-19
Dialogue & Discourse (published)
doi.org