Publications

Bernt Schiele

2017-01-25

International Journal of Computer Vision (published)

arxiv.org

Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus

Ryan Thomas Lowe

Nissan Pow

Iulian V. Serban

Laurent Charlin

Chia-Wei Liu

Joelle Pineau

In this paper, we construct and train end-to-end neural network-based dialogue systems using an updated version of the recent Ubuntu Dialogu… (see more)e 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.

2017-01-20

Dialogue & Discourse (published)

An Actor-Critic Algorithm for Sequence Prediction

Dzmitry Bahdanau

Philemon Brakel

Kelvin Xu

Anirudh Goyal

Ryan Lowe

Joelle Pineau

Yoshua Bengio

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.

2017-01-01

ICLR.cc/2017/conference (poster)

Adversarially Learned Inference

Vincent Dumoulin

Ishmael Belghazi

Ben Poole

Alex Lamb

Martin Arjovsky

Olivier Mastropietro

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.

2017-01-01

ICLR.cc/2017/conference (poster)

BOUNDS LEAD TO IMPROVED CLASSIFIERS

Nicolas Le Roux

The standard approach to supervised classification involves the minimization of a log-loss as an upper bound to the classification error. Wh… (see more)ile this is a tight bound early on in the optimization, it overemphasizes the influence of incorrectly classified examples far from the decision boundary. Updating the upper bound during the optimization leads to improved classification rates while transforming the learning into a sequence of minimization problems. In addition, in the context where the classifier is part of a larger system, this modification makes it possible to link the performance of the classifier to that of the whole system, allowing the seamless introduction of external constraints.

Brain tumor segmentation with Deep Neural Networks

Mohammad Havaei

Axel Davy

David Warde-Farley

Antoine Biard

Pierre-Marc Jodoin

2017-01-01

Medical Image Analysis (published)

arxiv.org

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.

2017-01-01

ICLR.cc/2017/conference (poster)

Computer Assisted and Robotic Endoscopy and Clinical Image-Based Procedures

M. Cardoso

Tal Arbel

Xiongbiao Luo

Stefan Wesarg

Tobias Reichl

M. Ballester

Jonathan Mcleod

Klaus Dr. Drechsler

T. Peters

Marius Erdt

Kensaku Mori

M. Linguraru

Andreas Uhl

Cristina Oyarzun Laura

R. Shekhar

2017-01-01

Lecture Notes in Computer Science (published)

Computer Assisted and Robotic Endoscopy and Clinical Image-Based Procedures

M. Jorge Cardoso

Tal Arbel

Xiongbiao Luo

Stefan Wesarg

Tobias Reichl

M. Ballester

Jonathan Mcleod

Klaus Dr. Drechsler

T. Peters

Marius Erdt

Kensaku Mori

M. Linguraru

Andreas Uhl

Cristina Oyarzun Laura

R. Shekhar

2017-01-01

Lecture Notes in Computer Science (published)

Computer-Assisted Conceptual Analysis of Textual Data as Applied to Philosophical Corpuses

Jean Guy Meunier

L. Chartrand

Jackie Cheung

Mathieu Valette

Marie-noëlle Bayle

2017-01-01

DH (published)

dblp.uni-trier.de

Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support

M. Jorge Cardoso

Tal Arbel

G. Carneiro

T. Syeda-Mahmood

J. Tavares

Mehdi Moradi

Andrew P. Bradley

Hayit Greenspan

J. Papa

Anant. Madabhushi

Jacinto C Nascimento

Jaime S. Cardoso

Vasileios Belagiannis

Zhi Lu

Faculdade Engenharia

2017-01-01

Lecture Notes in Computer Science (published)

arxiv.org

Diet Networks: Thin Parameters for Fat Genomics

Adriana Romero Soriano

Pierre Luc Carrier

Akram Erraqabi

Tristan Sylvain

Alex Auvolat

Etienne Dejoie

Marc-André Legault

Marie-Pierre Dubé

Julie Hussin

Yoshua Bengio

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (see more) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.

2017-01-01

ICLR.cc/2017/conference (poster)