Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
Matt Grenander
Yue Dong
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… (voir plus). 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.
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods c… (voir plus)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.
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
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challeng… (voir plus)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.
Interactive Language Learning by Question Answering
Xingdi Yuan
Marc-Alexandre Côté
Jie Fu
Zhouhan Lin
Adam Trischler
Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the i… (voir plus)nteractive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.
A Reduction from Reinforcement Learning to No-Regret Online Learning
Ching-An Cheng
Remi Tachet des Combes
Byron Boots
We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "… (voir plus)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
Referring Expression Generation Using Entity Profiles
Meng Cao
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
A deep learning framework for neuroscience
Timothy P. Lillicrap
Philippe Beaudoin
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 … (voir 12 de plus)
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
Collegiality as political work: Professions in today’s world of organizations
Jean-Louis Denis
Gianluca Veronesi
Sabrina Germain
Collegiality is frequently portrayed as an inherent characteristic of professions, associated with normative expectations autonomously deter… (voir plus)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.
Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
Shawn Tan
Guillaume Androz
Ahmad Chamseddine
Pierre Fecteau
Joseph Paul Cohen
We release the largest public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billio… (voir plus)n labelled beats. Our goal is to enable semi-supervised ECG models to be made as well as to discover unknown subtypes of arrhythmia and anomalous ECG signal events. To this end, we propose an unsupervised representation learning task, evaluated in a semi-supervised fashion. We provide a set of baselines for different feature extractors that can be built upon. Additionally, we perform qualitative evaluations on results from PCA embeddings, where we identify some clustering of known subtypes indicating the potential for representation learning in arrhythmia sub-type discovery.
Continual Learning of New Sound Classes Using Generative Replay
Zhepei Wang
Efthymios Tzinis
Paris Smaragdis
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this pa… (voir plus)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.
Predicting ice flow using machine learning
Yimeng Min
S. Karthik Mukkavilli
Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, … (voir plus)applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future video frame prediction, to increase the accuracy of ice flow tracking in multi-spectral satellite images. As the volume of cryosphere data increases in coming years, this is an interesting and important opportunity for machine learning to address a global challenge for climate change, risk management from floods, and conserving freshwater resources. Future frame prediction of ice melt and tracking the optical flow of ice dynamics presents modeling difficulties, due to uncertainties in global temperature increase, changing precipitation patterns, occlusion from cloud cover, rapid melting and glacier retreat due to black carbon aerosol deposition, from wildfires or human fossil emissions. We show the adversarial learning method helps improve the accuracy of tracking the optical flow of ice dynamics compared to existing methods in climate science. We present a dataset, IceNet, to encourage machine learning research and to help facilitate further applications in the areas of cryospheric science and climate change.