Yoshua Bengio

TL;DR: HotpotQA as discussed by the authors is a dataset with 113k Wikipedia-based question-answer pairs with four key features: finding and reasoning over multiple supporting documents to answer; the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; providing sentence-level supporting facts required for reasoning; and offering a new type of factoid comparison questions to test QA systems' ability to extract relevant facts and perform necessary comparison.

TL;DR: Deep Graph Infomax (DGI) is presented, a general approach for learning node representations within graph-structured data in an unsupervised manner that is readily applicable to both transductive and inductive learning setups.

TL;DR: A Mutual Information Neural Estimator (MINE) is presented that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent, and applied to improve adversarially trained generative models.

TL;DR: In this article, the authors explore the use of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder.

TL;DR: This work proves that adding hidden units yields strictly improved modeling power, while a second theorem shows that RBMs are universal approximators of discrete distributions and suggests a new and less greedy criterion for training RBMs within DBNs.