activity
20172020
collaborators

8 papers

cs.LG2020

Meta Pseudo Labels

Hieu Pham, Zihang Dai, Qizhe Xie +2

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing st…

cs.LG2019

Self-training with Noisy Student improves ImageNet classification

Qizhe Xie, Minh-Thang Luong, Eduard Hovy +1

We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on I…

cs.LG2019

Unsupervised Data Augmentation for Consistency Training

Qizhe Xie, Zihang Dai, Eduard Hovy +2

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency train…

cs.AI2018

The Profiling Machine: Active Generalization over Knowledge

Filip Ilievski, Eduard Hovy, Qizhe Xie +1

The human mind is a powerful multifunctional knowledge storage and management system that performs generalization, type inference, anomaly detection, stereotyping, and other tasks.…

cs.CL2018

Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation

Xiang Kong, Qizhe Xie, Zihang Dai +1

Mixture of Softmaxes (MoS) has been shown to be effective at addressing the expressiveness limitation of Softmax-based models. Despite the known advantage, MoS is practically seale…

cs.CL2018

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction

Zihang Dai, Qizhe Xie, Eduard Hovy

In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counter…