Publications

Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
Matt Grenander
Yue Dong
Jackie Cheung
Annie Priyadarshini Louis
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article… (see more). In this paper, we show that recent neural systems excessively exploit this trend, which although powerful for many inputs, is also detrimental when summarizing documents where important content should be extracted from later parts of the article. We propose two techniques to make systems sensitive to the importance of content in different parts of the article. The first technique employs ‘unbiased’ data; i.e., randomly shuffled sentences of the source document, to pretrain the model. The second technique uses an auxiliary ROUGE-based loss that encourages the model to distribute importance scores throughout a document by mimicking sentence-level ROUGE scores on the training data. We show that these techniques significantly improve the performance of a competitive reinforcement learning based extractive system, with the auxiliary loss being more powerful than pretraining.
2019-11-01
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Tianyu Li
Bogdan Mazoure
Doina Precup
Guillaume Rabusseau
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods c… (see more)onsider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predicitive state representations and offers appealing theoretical guarantees and time complexity. We empirically show on two domains that our approach is more sample and time efficient compared to classical methods.
2019-11-01
ArXiv (preprint)
arxiv.org
arxiv.org
How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG
Paul Trichelair
Ali Emami
Adam Trischler
Kaheer Suleman
Jackie Cheung
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challeng… (see more)e (WSC) and SWAG. The question we ask in this paper is whether improved performance on these benchmarks represents genuine progress towards common-sense-enabled systems. We make case studies of both benchmarks and design protocols that clarify and qualify the results of previous work by analyzing threats to the validity of previous experimental designs. Our protocols account for several properties prevalent in common-sense benchmarks including size limitations, structural regularities, and variable instance difficulty.
2019-11-01
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng
Remi Tachet des Combes
Byron Boots
Geoff Gordon
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (see more)any" online algorithm with sublinear regret can generate policies with provable performance guarantees. This new perspective decouples the RL problem into two parts: regret minimization and function approximation. The first part admits a standard online-learning analysis, and the second part can be quantified independently of the learning algorithm. Therefore, the proposed reduction can be used as a tool to systematically design new RL algorithms. We demonstrate this idea by devising a simple RL algorithm based on mirror descent and the generative-model oracle. For any
2019-11-01
ArXiv (preprint)
arxiv.org
arxiv.org
Referring Expression Generation Using Entity Profiles
Meng Cao
Jackie Cheung
2019-11-01
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (published)
doi.org
arxiv.org
Fluoroquinolone Use and Seasonal Patterns of Ciprofloxacin Resistance in Community-Acquired Urinary Escherichia coli Infection in a Large Urban Center
Jean-Paul R Soucy
Alexandra M. Schmidt
Caroline Quach
David Buckeridge
2019-10-29
American Journal of Epidemiology (published)
doi.org
A deep learning framework for neuroscience
Blake Richards
Timothy P. Lillicrap
Philippe Beaudoin
Yoshua Bengio
Rafal Bogacz
Amelia Christensen
Claudia Clopath
Rui Ponte Costa
Archy de Berker
Surya Ganguli
Colleen J Gillon
Danijar Hafner
Adam Kepecs
Nikolaus Kriegeskorte
Peter Latham
Grace W. Lindsay
Kenneth D. Miller
Richard Naud
Christopher C. Pack
Panayiota Poirazi … (see 12 more)
Pieter Roelfsema
João Sacramento
Andrew Saxe
Benjamin Scellier
Anna C. Schapiro
Walter Senn
Greg Wayne
Daniel Yamins
Friedemann Zenke
Joel Zylberberg
Denis Therien
Konrad Paul Kording
2019-10-28
Nature Neuroscience (published)
doi.org
Collegiality as political work: Professions in today’s world of organizations
Jean-Louis Denis
Gianluca Veronesi
Catherine Régis
Sabrina Germain
Collegiality is frequently portrayed as an inherent characteristic of professions, associated with normative expectations autonomously deter… (see more)mined and regulated among peers. However, in advanced modernity other modes of governance responding to societal expectations and increasing state reliance on professional expertise often appear in tension with conditions of collegiality. This article argues that collegiality is not an immutable and inherent characteristic of the governance of professional work and organizations; rather, it is the result of the ability of a profession to operationalize the normative, relational, and structural requirements of collegiality at work. This article builds on different streams of scholarship to present a dynamic approach to collegiality based on political work by professionals to protect, maintain, and reformulate collegiality as a core set of principles governing work. Productive resistance and co-production are explored for their contribution to collegiality in this context, enabling accommodation between professions and organizations to achieve collective objectives and serving as a vector of change and adaptation of professional work in contemporary organizations. Engagement in co-production influences the ability to materialize collegiality at work, just as the maintenance and transformation of collegiality will operate in a context where professions participate and negotiate compromises with others legitimate modes of governance. Our arguments build on recent studies and hypotheses concerning the interface of professions and organizations to reveal the political work that underlies the affirmation and re-affirmation of collegiality as a mode of governance of work based on resistance and co-production.
2019-10-24
Journal of Professions and Organization (published)
doi.org
Continual Learning of New Sound Classes Using Generative Replay
Zhepei Wang
Cem (Yusuf) Subakan
Efthymios Tzinis
Paris Smaragdis
Laurent Charlin
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this pa… (see more)per, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as "catastrophic forgetting." We develop a generative replay procedure for generating training audio spectrogram data, in place of keeping older training datasets. We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data. We thus conclude that we can extend a trained sound classifier to learn new classes without having to keep previously used datasets.
2019-10-20
2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (published)
doi.org
arxiv.org
Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference
Raghav Mehta
Thomas Christinck
Tanya Nair
Aurélie Bussy
Paul Lemaitre
Swapna Premasiri
Douglas Arnold
Manuela Costantino
Tal Arbel
Mallar Chakravarty
Yarin Gal
Although deep networks have been shown to perform very well on a variety of medical imaging tasks, inference in the presence of pathology pr… (see more)esents several challenges to common models. These challenges impede the integration of deep learning models into real clinical workflows, where the customary process of cascading deterministic outputs from a sequence of image-based inference steps (e.g. registration, segmentation) generally leads to an accumulation of errors that impacts the accuracy of downstream inference tasks. In this paper, we propose that by embedding uncertainty estimates across cascaded inference tasks, performance on the downstream inference tasks should be improved. We demonstrate the effectiveness of the proposed approach in three different clinical contexts: (i) We demonstrate that by propagating T2 weighted lesion segmentation results and their associated uncertainties, subsequent T2 lesion detection performance is improved when evaluated on a proprietary large-scale, multi-site, clinical trial dataset acquired from patients with Multiple Sclerosis. (ii) We show an improvement in brain tumour segmentation performance when the uncertainty map associated with a synthesised missing MR volume is provided as an additional input to a follow-up brain tumour segmentation network, when evaluated on the publicly available BraTS-2018 dataset. (iii) We show that by propagating uncertainties from a voxel-level hippocampus segmentation task, the subsequent regression of the Alzheimer’s disease clinical score is improved.
2019-10-17
UNSURE/CLIP@MICCAI (published)
doi.org
Saliency Based Deep Neural Network for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI
Joshua D. Durso-Finley
Douglas Arnold
Tal Arbel
2019-10-17
BrainLes@MICCAI (published)
doi.org
SGP: Spotting Groups Polluting the Online Political Discourse
Junhao Wang
Sacha Lévy
Ren Wang
Aayushi Kulshrestha
Reihaneh Rabbany
Social media sites are becoming a key factor in politics. These platforms are easy to manipulate for the purpose of distorting information s… (see more)pace to confuse and distract voters. It is of paramount importance for social media platforms, users engaged with online political discussions, as well as government agencies to understand the dynamics on social media, and identify malicious groups engaging in misinformation campaigns and thus polluting the general discourse around a topic of interest. Past works to identify such disruptive patterns are mostly focused on analyzing user-generated content such as tweets. In this study, we take a holistic approach and propose SGP to provide an informative birds eye view of all the activities in these social media sites around a broad topic and detect coordinated groups suspicious of engaging in misinformation campaigns. To show the effectiveness of SGP, we deploy it to provide a concise overview of polluting activity on Twitter around the upcoming 2019 Canadian Federal Elections, by analyzing over 60 thousand user accounts connected through 3.4 million connections and 1.3 million hashtags. Users in the polluting groups detected by SGP-flag are over 4x more likely to become suspended while majority of these highly suspicious users detected by SGP-flag escaped Twitter's suspending algorithm. Moreover, while few of the polluting hashtags detected are linked to misinformation campaigns, SGP-sig also flags others that have not been picked up on. More importantly, we also show that a large coordinated set of right-winged conservative groups based in the US are heavily engaged in Canadian politics.
2019-10-16
ArXiv (preprint)
arxiv.org
arxiv.org