Publications

Neural Network Based Nonlinear Weighted Finite Automata
Tianyu Li
Guillaume Rabusseau
Doina Precup
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models. Given the recent succ… (see more)esses of nonlinear models in machine learning, it is natural to wonder whether ex-tending WFA to the nonlinear setting would be beneficial. In this paper, we propose a novel model of neural network based nonlinearWFA model (NL-WFA) along with a learning algorithm. Our learning algorithm is inspired by the spectral learning algorithm for WFAand relies on a nonlinear decomposition of the so-called Hankel matrix, by means of an auto-encoder network. The expressive power of NL-WFA and the proposed learning algorithm are assessed on both synthetic and real-world data, showing that NL-WFA can lead to smaller model sizes and infer complex grammatical structures from data.
2017-09-12
ArXiv (preprint)
arxiv.org
arxiv.org
Predicting Future Disease Activity and Treatment Responders for Multiple Sclerosis Patients Using a Bag-of-Lesions Brain Representation
Andrew Doyle
Doina Precup
Douglas Arnold
Tal Arbel
2017-09-09
International Conference on Medical Image Computing and Computer-Assisted Intervention (published)
doi.org
A Deep Reinforcement Learning Chatbot
Iulian V. Serban
Chinnadhurai Sankar
Mathieu Germain
Saizheng Zhang
Zhouhan Lin
Sandeep Subramanian
Taesup Kim
Michael Pieper
Sarath Chandar
Nan Rosemary Ke
Sai Mudumba
Alexandre De Brébisson
Jose M. R. Sotelo
Dendi Suhubdy
Vincent Michalski
Alexandre Nguyen
Joelle Pineau
Yoshua Bengio
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (see more)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.
2017-09-06
ArXiv (preprint)
doi.org
arxiv.org
Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics
M. Jorge Cardoso
Tal Arbel
Enzo Ferrante
Xavier Pennec
Adrian Dalca
Sarah Parisot
S. Joshi
Nematollah Batmanghelich
Aristeidis Sotiras
Mads Lenstrup Nielsen
Mert R. Sabuncu
Tom Fletcher
Li Shen
Stanley Durrleman
Stefan H. Sommer
2017-08-31
Lecture Notes in Computer Science (published)
doi.org
Horizontal and Vertical Self-Adaptive Cloud Controller with Reward Optimization for Resource Allocation
Jesús Alejandro Cárdenes Cabré
Doina Precup
Ricardo Sanz
Over-booking or under-booking of computing resources leads to higher cost and performance degradation of web applications. To optimize the p… (see more)erformance of web applications, access to the resources has to be dynamically controlled ensuring maximum cost-performance ratio of the application while fulfilling requirements. To simplify the design of dynamic cloud controllers, we propose a horizontal and vertical scalability self-aware agent defined by a self-adaptive fuzzy logic with an oriented random optimizer based on reward and memory. The algorithm dynamically adjusts the membership functions and their relationship, maximizing the reward of the system while considering the cost related to the deployment of new resources. The evaluation of the controller under real cloud workload reveals the ability of the algorithm to maximize the performance of the web application based on the target parameters given by an operator.
2017-08-31
International Conference on Cloud and Autonomic Computing (published)
doi.org
On integrating a language model into neural machine translation
Caglar Gulçehre
Orhan Firat
Kelvin Xu
Kyunghyun Cho
Yoshua Bengio
2017-08-31
Computer Speech and Language (published)
doi.org
Multi-way, multilingual neural machine translation
Orhan Firat
Kyunghyun Cho
Baskaran Sankaran
F. Yarman-Vural
Yoshua Bengio
2017-08-31
Computer Speech and Language (published)
doi.org
Piecewise Latent Variables for Neural Variational Text Processing
Iulian V. Serban
Alexander G. Ororbia II
Joelle Pineau
Aaron Courville
Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variable… (see more)s, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.
2017-08-31
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (published)
doi.org
arxiv.org
World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions
Teng Long
Emmanuel Bengio
Ryan Lowe
Jackie CK Cheung
Doina Precup
Humans interpret texts with respect to some background information, or world knowledge, and we would like to develop automatic reading compr… (see more)ehension systems that can do the same. In this paper, we introduce a task and several models to drive progress towards this goal. In particular, we propose the task of rare entity prediction: given a web document with several entities removed, models are tasked with predicting the correct missing entities conditioned on the document context and the lexical resources. This task is challenging due to the diversity of language styles and the extremely large number of rare entities. We propose two recurrent neural network architectures which make use of external knowledge in the form of entity descriptions. Our experiments show that our hierarchical LSTM model performs significantly better at the rare entity prediction task than those that do not make use of external resources.
2017-08-31
Conference on Empirical Methods in Natural Language Processing (published)
doi.org
Glucocorticoid sensitivity in a subset of human RUNX1-mutated acute myeloid leukemia
Frédéric Leduc
Maude Wur
Geneviève Boucher
Rose-Marie Rébillard
Valérie Bordeleau
Julie Bergeron
Nadine Mayotte
Anne-Marie Côté
Véronique Lisi
Elliot D. Drobetsky
Tarik Möröy
Lambert Busque
Jean-Sébastien Delisle
Martin Sauvageau
Sébastien Lemieux
Josée Hébert
Guy Sauvageau
Purpose: RUNX1-mutated (RUNX1mut) acute myeloid leukemia (AML) is associated with adverse outcome, highlighting the urgent need for a bett… (see more)er genetic characterization of this AML subgroup and for the design of efficient therapeutic strategies for this disease. Toward this goal, we further dissected the mutational spectrum and gene expression profile of RUNX1mut AML and correlated these results to drug sensitivity to identify novel compounds targeting this AML subgroup. Experimental Design: RNA-sequencing of 47 RUNX1mut primary AML specimens was performed and sequencing results were compared to those of RUNX1 wild-type samples. Chemical screens were also conducted using RUNX1mut specimens to identify compounds selectively affecting the viability of RUNX1mut AML. Results: We show that samples with no remaining RUNX1 wild-type allele are clinically and genetically distinct and display a more homogeneous gene expression profile. Chemical screening revealed that most RUNX1mut specimens are sensitive to glucocorticoids (GCs) and we confirmed that GCs inhibit AML cell proliferation through their interaction with the glucocorticoid receptor (GR). We observed that specimens harboring RUNX1 mutations expected to result in low residual RUNX1 activity are most sensitive to GCs, and that coassociating mutations as well as GR levels contribute to GC sensitivity. Accordingly, acquired glucocorticoid sensitivity was achieved by negatively regulating RUNX1 expression in human AML cells. Conclusions: Our findings show the profound impact of RUNX1 allele dosage on gene expression profile and glucocorticoid sensitivity in AML, thereby opening opportunities for preclinical testing which may lead to drug repurposing and improved disease characterization. Clin Cancer Res; 23(22); 6969–81. ©2017 AACR.
2017-08-30
Clinical Cancer Research (unknown)
doi.org
Twin Networks: Using the Future as a Regularizer
Dmitriy Serdyuk
Nan Rosemary Ke
Alessandro Sordoni
Christopher Pal
Yoshua Bengio
Being able to model long-term dependencies in sequential data, such as text, has been among the long-standing challenges of recurrent neural… (see more) networks (RNNs). This issue is strictly related to the absence of explicit planning in current RNN architectures. More explicitly, the RNNs are trained to predict only the next token given previous ones. In this paper, we introduce a simple way of encouraging the RNNs to plan for the future. In order to accomplish this, we introduce an additional neural network which is trained to generate the sequence in reverse order, and we require closeness between the states of the forward RNN and backward RNN that predict the same token. At each step, the states of the forward RNN are required to match the future information contained in the backward states. We hypothesize that the approach eases modeling of long-term dependencies thus helping in generating more globally consistent samples. The model trained with conditional generation for a speech recognition task achieved 12\% relative improvement (CER of 6.7 compared to a baseline of 7.6).
2017-08-21
ArXiv (preprint)
arxiv.org
arxiv.org
Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
Taesup Kim
Inchul Song
Yoshua Bengio
Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the trai… (see more)ning speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, our proposed approach does not require additional adaptation data or speaker information such as i-vectors. Moreover, the model size is fixed as it dynamically generates adaptation parameters. We apply our proposed DLN to deep bidirectional LSTM acoustic models and evaluate them on two benchmark datasets for large vocabulary ASR experiments: WSJ and TED-LIUM release 2. The experimental results show that our DLN improves neural acoustic models in terms of transcription accuracy by dynamically adapting to various speakers and environments.
2017-08-19
Interspeech 2017 (published)
doi.org
arxiv.org