Publications

Defining ‘actionable’ high- costhealth care use: results using the Canadian Institute for Health Information population grouping methodology

Maureen Anderson

Crawford W. Revie

Henrik Stryhn

Cordell Neudorf

Yvonne Rosehart

Wenbin Li

Meriç Osman

David Buckeridge

Laura C. Rosella

Walter P. Wodchis

2019-11-10

International Journal for Equity in Health (publié)

Preventing Posterior Collapse in Sequence VAEs with Pooling

Teng Long

Yanshuai Cao

Variational Autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic … (voir plus)properties from local regularities of natural language. Practically, however, VAEs with autoregressive decoders often suffer from posterior collapse, a phenomenon where the model learns to ignore the latent variables, causing the sequence VAE to degenerate into a language model. Previous works attempt to solve this problem with complex architectural changes or costly optimization schemes. In this paper, we argue that posterior collapse is caused in part by the encoder network failing to capture the input variabilities. We verify this hypothesis empirically and propose a straightforward fix using pooling. This simple technique effectively prevents posterior collapse, allowing the model to achieve significantly better data log-likelihood than standard sequence VAEs. Compared to the previous SOTA on preventing posterior collapse, we are able to achieve comparable performances while being significantly faster.

2019-11-10

ArXiv (prépublication)

Adversarial target-invariant representation learning for domain generalization

Isabela Albuquerque

Joao Monteiro

Tiago Falk

Ioannis Mitliagkas

In many applications of machine learning, the training and test set data come from different distributions, or domains. A number of domain g… (voir plus)eneralization strategies have been introduced with the goal of achieving good performance on out-of-distribution data. In this paper, we propose an adversarial approach to the problem. We propose a process that enforces pair-wise domain invariance while training a feature extractor over a diverse set of domains. We show that this process ensures invariance to any distribution that can be expressed as a mixture of the training domains. Following this insight, we then introduce an adversarial approach in which pair-wise divergences are estimated and minimized. Experiments on two domain generalization benchmarks for object recognition (i.e., PACS and VLCS) show that the proposed method yields higher average accuracy on the target domains in comparison to previously introduced adversarial strategies, as well as recently proposed methods based on learning invariant representations.

2019-11-03

arXiv.org (prépublication)

dblp.uni-trier.de

Generalizing to unseen domains via distribution matching

Isabela Albuquerque

Joao Monteiro

Mohammad-Javad Darvishi-Bayazi

Tiago Falk

Ioannis Mitliagkas

Supervised learning results typically rely on assumptions of i.i.d. data. Unfortunately, those assumptions are commonly violated in practice… (voir plus). In this work, we tackle this problem by focusing on domain generalization: a formalization where the data generating process at test time may yield samples from never-before-seen domains (distributions). Our work relies on a simple lemma: by minimizing a notion of discrepancy between all pairs from a set of given domains, we also minimize the discrepancy between any pairs of mixtures of domains. Using this result, we derive a generalization bound for our setting. We then show that low risk over unseen domains can be achieved by representing the data in a space where (i) the training distributions are indistinguishable, and (ii) relevant information for the task at hand is preserved. Minimizing the terms in our bound yields an adversarial formulation which estimates and minimizes pairwise discrepancies. We validate our proposed strategy on standard domain generalization benchmarks, outperforming a number of recently introduced methods. Notably, we tackle a real-world application where the underlying data corresponds to multi-channel electroencephalography time series from different subjects, each considered as a distinct domain.

2019-11-03

ArXiv (prépublication)

Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text

Ian Porada

Kaheer Suleman

2019-11-01

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing (publié)

CoQA: A Conversational Question Answering Challenge

Siva Reddy

Danqi Chen

Christopher D. Manning

Humans gather information through conversations involving a series of interconnected questions and answers. For machines to assist in inform… (voir plus)ation gathering, it is therefore essential to enable them to answer conversational questions. We introduce CoQA, a novel dataset for building Conversational Question Answering systems. Our dataset contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains. The questions are conversational, and the answers are free-form text with their corresponding evidence highlighted in the passage. We analyze CoQA in depth and show that conversational questions have challenging phenomena not present in existing reading comprehension datasets (e.g., coreference and pragmatic reasoning). We evaluate strong dialogue and reading comprehension models on CoQA. The best system obtains an F1 score of 65.4%, which is 23.4 points behind human performance (88.8%), indicating that there is ample room for improvement. We present CoQA as a challenge to the community at https://stanfordnlp.github.io/coqa.

2019-11-01

Transactions of the Association for Computational Linguistics (publié)

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.

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) (publié)

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… (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.

2019-11-01

ArXiv (preprint)

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.

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) (publié)

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 "… (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

2019-11-01

ArXiv (preprint)

Referring Expression Generation Using Entity Profiles

Meng Cao

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) (publié)