Aaron Courville

alan.milligan@mila.quebec

Alan Alan

PhD - Université de Montréal

Principal supervisor :

Simon Lacoste-Julien

Anirudh Buvanesh

PhD - Université de Montréal

Principal supervisor :

Laurent Charlin

anirudb1102@gmail.com

sarvjeet-singh.ghotra@mila.quebec

Juan Duque

PhD - Université de Montréal

juan.duque@mila.quebec

PhD - Université de Montréal

udaykaran.kapur@mila.quebec

Arian Hosseini

PhD - Université de Montréal

Uday Kapur

PhD - Université de Montréal

Amr Khalifa

PhD - Université de Montréal

amr-khalifa.alshaykh@mila.quebec

andjela.mladenovic@mila.quebec

Zhixuan Lin

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Pablo Samuel Castro

waltermayor@gmail.com

PhD - Université de Montréal

Principal supervisor :

Gauthier Gidel

mohammed.muqeeth@mila.quebec

Muqeeth Mohammed

PhD - Université de Montréal

PhD - Université de Montréal

Co-supervisor :

Rishabh Agarwal

morgane.moss@mila.quebec

Andrei Nicolicioiu

PhD - Université de Montréal

andrei.nicolicioiu@gmail.com

michell.payanoperez@mila.quebec

Michael Noukhovitch

PhD - Université de Montréal

Johan Samir Obando Ceron

PhD - Université de Montréal

Co-supervisor :

Pablo Samuel Castro

johan.ceron@mila.quebec

PhD - Université de Montréal

Dereck Piché

PhD - Université de Montréal

pichedereck@gmail.com

khaled.rouissi@mila.quebec

Khaled Rouissi

Master's Research - Université de Montréal

Esra'a Saleh

PhD - Université de Montréal

Principal supervisor :

Glen Berseth

esraa.saleh@mila.quebec

Vedant Shah

PhD - Université de Montréal

vedant.shah@mila.quebec

colin.yiyang-lu@mila.quebec

Yusong Wu

PhD - Université de Montréal

Principal supervisor :

Anna (Cheng-Zhi) Huang

wu.yusong@mila.quebec

Colin Yiyang Lu

PhD - Université de Montréal

Sujin yun

PhD - Université de Montréal

sujin.yun@mila.quebec

xiaofeng.zhang@mila.quebec

Xiaofeng Zhang

PhD - Université de Montréal

Publications

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Iulian V. Serban

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)

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

Iulian V. Serban

Tim Klinger

Gerald Tesauro

Kartik Talamadupula

Bowen Zhou

Yoshua Bengio

We introduce a new class of models called multiresolution recurrent neural networks, which explicitly model natural language generation at m… (see more)ultiple levels of abstraction. The models extend the sequence-to-sequence framework to generate two parallel stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language words (e.g. sentences). The coarse sequences follow a latent stochastic process with a factorial representation, which helps the models generalize to new examples. The coarse sequences can also incorporate task-specific knowledge, when available. In our experiments, the coarse sequences are extracted using automatic procedures, which are designed to capture compositional structure and semantics. These procedures enable training the multiresolution recurrent neural networks by maximizing the exact joint log-likelihood over both sequences. We apply the models to dialogue response generation in the technical support domain and compare them with several competing models. The multiresolution recurrent neural networks outperform competing models by a substantial margin, achieving state-of-the-art results according to both a human evaluation study and automatic evaluation metrics. Furthermore, experiments show the proposed models generate more fluent, relevant and goal-oriented responses.

2017-02-11

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Multiresolution Recurrent Neural Networks: An Application to Dialogue\n Response Generation

Iulian Vlad Serban

Tim Klinger

Gerald Tesauro

Kartik Talamadupula

Bowen Zhou

Yoshua Bengio

We introduce the multiresolution recurrent neural network, which extends the\nsequence-to-sequence framework to model natural language gener… (see more)ation as two\nparallel discrete stochastic processes: a sequence of high-level coarse tokens,\nand a sequence of natural language tokens. There are many ways to estimate or\nlearn the high-level coarse tokens, but we argue that a simple extraction\nprocedure is sufficient to capture a wealth of high-level discourse semantics.\nSuch procedure allows training the multiresolution recurrent neural network by\nmaximizing the exact joint log-likelihood over both sequences. In contrast to\nthe standard log- likelihood objective w.r.t. natural language tokens (word\nperplexity), optimizing the joint log-likelihood biases the model towards\nmodeling high-level abstractions. We apply the proposed model to the task of\ndialogue response generation in two challenging domains: the Ubuntu technical\nsupport domain, and Twitter conversations. On Ubuntu, the model outperforms\ncompeting approaches by a substantial margin, achieving state-of-the-art\nresults according to both automatic evaluation metrics and a human evaluation\nstudy. On Twitter, the model appears to generate more relevant and on-topic\nresponses according to automatic evaluation metrics. Finally, our experiments\ndemonstrate that the proposed model is more adept at overcoming the sparsity of\nnatural language and is better able to capture long-term structure.\n

2017-02-11

AAAI Conference on Artificial Intelligence (published)

Adversarially Learned Inference

Vincent Dumoulin

Ishmael Belghazi

Ben Poole

We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an ad… (see more)versarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the space of latent variables. An adversarial game is cast between these two networks and a discriminative network is trained to distinguish between joint latent/data-space samples from the generative network and joint samples from the inference network. We illustrate the ability of the model to learn mutually coherent inference and generation networks through the inspections of model samples and reconstructions and confirm the usefulness of the learned representations by obtaining a performance competitive with state-of-the-art on the semi-supervised SVHN and CIFAR10 tasks.

2017-02-05

International Conference on Learning Representations (poster)

Calibrating Energy-based Generative Adversarial Networks

Zihang Dai

Amjad Almahairi

Philip Bachman

Eduard Hovy

In this paper, we propose to equip Generative Adversarial Networks with the ability to produce direct energy estimates for samples. Specific… (see more)ally, we propose a flexible adversarial training framework, and prove this framework not only ensures the generator converges to the true data distribution, but also enables the discriminator to retain the density information at the global optimal. We derive the analytic form of the induced solution, and analyze the properties. In order to make the proposed framework trainable in practice, we introduce two effective approximation techniques. Empirically, the experiment results closely match our theoretical analysis, verifying the discriminator is able to recover the energy of data distribution.

2017-02-05

ICLR.cc/2017/conference (poster)

PixelVAE: A Latent Variable Model for Natural Images

Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representatio… (see more)n and model global structure well but have difficulty capturing small details. PixelCNN models details very well, but lacks a latent code and is difficult to scale for capturing large structures. We present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. Our model requires very few expensive autoregressive layers compared to PixelCNN and learns latent codes that are more compressed than a standard VAE while still capturing most non-trivial structure. Finally, we extend our model to a hierarchy of latent variables at different scales. Our model achieves state-of-the-art performance on binarized MNIST, competitive performance on 64 × 64 ImageNet, and high-quality samples on the LSUN bedrooms dataset.

2017-02-05

ICLR.cc/2017/conference (poster)

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

Jose Sotelo

In this paper we propose a novel model for unconditional audio generation task that generates one audio sample at a time. We show that our m… (see more)odel which profits from combining memory-less modules, namely autoregressive multilayer perceptron, and stateful recurrent neural networks in a hierarchical structure is de facto powerful to capture the underlying sources of variations in temporal domain for very long time on three datasets of different nature. Human evaluation on the generated samples indicate that our model is preferred over competing models. We also show how each component of the model contributes to the exhibited performance.

2017-02-05

ICLR.cc/2017/conference (poster)

Movie Description

Anna Rohrbach

Atousa Torabi

Marcus Rohrbach

Niket Tandon

Christopher Pal

Hugo Larochelle

Bernt Schiele

Audio description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their pee… (see more)rs. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. We introduce the Large Scale Movie Description Challenge (LSMDC) which contains a parallel corpus of 128,118 sentences aligned to video clips from 200 movies (around 150 h of video in total). The goal of the challenge is to automatically generate descriptions for the movie clips. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in the challenges organized in the context of two workshops at ICCV 2015 and ECCV 2016.

2017-01-24

International Journal of Computer Vision (published)

An Actor-Critic Algorithm for Sequence Prediction

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Curren… (see more)t log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \textit{critic} network that is trained to predict the value of an output token, given the policy of an \textit{actor} network. This results in a training procedure that is much closer to the test phase, and allows us to directly optimize for a task-specific score such as BLEU. Crucially, since we leverage these techniques in the supervised learning setting rather than the traditional RL setting, we condition the critic network on the ground-truth output. We show that our method leads to improved performance on both a synthetic task, and for German-English machine translation. Our analysis paves the way for such methods to be applied in natural language generation tasks, such as machine translation, caption generation, and dialogue modelling.

2016-12-31

ICLR.cc/2017/conference (poster)

Counterpoint by Convolution

Cheng-Zhi Anna Huang

Tim Cooijmans

Adam Roberts

Douglas Eck

Machine learning models of music typically break down the task of composition into a chronological process, composing a piece of music in a … (see more)single pass from beginning to end. On the contrary, human composers write music in a nonlinear fashion, scribbling motifs here and there, often revisiting choices previously made. We explore the use of blocked Gibbs sampling as an analogue to the human approach, and introduce Coconet, a convolutional neural network in the NADE family of generative models. Despite ostensibly sampling from the same distribution as the NADE ancestral sampling procedure, we find that a blocked Gibbs approach significantly improves sample quality. We provide evidence that this is due to some conditional distributions being poorly modeled. Moreover, we show that even the cheap approximate blocked Gibbs procedure from Yao et al. (2014) yields better samples than ancestral sampling. We demonstrate the versatility of our method on unconditioned polyphonic music generation.

2016-12-31

Zenodo (published)

Facilitating Multimodality in Normalizing Flows

Chin-wei Huang

David M. Krueger

The true Bayesian posterior of a model such as a neural network may be highly multimodal. In principle, normalizing flows can represent such… (see more) a distribution via compositions of invertible transformations of random noise. In practice, however, existing normalizing flows may fail to capture most of the modes of a distribution. We argue that the conditionally affine structure of the transformations used in [Dinh et al., 2014, 2016, Kingma et al., 2016] is inefficient, and show that flows which instead use (conditional) invertible non-linear transformations naturally enable multimodality in their output distributions. With just two layers of our proposed deep sigmoidal flow, we are able to model complicated 2d energy functions with much higher fidelity than six layers of deep affine flows.

2016-12-31

(published)

www.semanticscholar.org

Generalizable Features From Unsupervised Learning

Mehdi Mirza

Yoshua Bengio

Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast t… (see more)o most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is physical intuition(Lake et al., 2016). In this work, we explore the potential of unsupervised learning to find features that promote better generalization to settings outside the supervised training distribution. Our task is predicting the stability of towers of square blocks. We demonstrate that an unsupervised model, trained to predict future frames of a video sequence of stable and unstable block configurations, can yield features that support extrapolating stability prediction to blocks configurations outside the training set distribution

2016-12-31

ICLR.cc/2017/conference (Invite to Workshop Track)