Minh-Thang Luong

Publications
Influence

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

Adams Wei Yu, David Dohan, +4 authors Quoc V. Le
Computer Science
ICLR
15 February 2018

We propose a new Q\&A architecture called QANet, which does not require recurrent networks: Its encoder consists exclusively of convolution and self-attention, where convolution models local interactions and selfattention models global interactions. Expand

Multi-task Sequence to Sequence Learning

Minh-Thang Luong, Quoc V. Le, Ilya Sutskever, Oriol Vinyals, L. Kaiser
Computer Science, Mathematics
ICLR
19 November 2015

This paper examines three multi-task learning (MTL) settings for sequence to sequence models: (a) the oneto-many setting - where the encoder is shared between several tasks such as machine translation and syntactic parsing, (b) the many-to-one setting - useful when only the decoder can be shared, as in the case of translation and image caption generation, which is the case with unsupervised objectives and translation. Expand

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

K. Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning
Computer Science
ICLR
23 March 2020

We propose a new pre-training task called replaced token detection. Expand

A Hierarchical Neural Autoencoder for Paragraphs and Documents

J. Li, Minh-Thang Luong, Dan Jurafsky
Computer Science
ACL
2 June 2015

We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. Expand

Self-Training With Noisy Student Improves ImageNet Classification

Qizhe Xie, E. Hovy, Minh-Thang Luong, Quoc V. Le
Computer Science, Mathematics
IEEE/CVF Conference on Computer Vision and…
11 November 2019

We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the previous state-of-the-art model that requires 3.5B weakly labeled Instagram images. Expand

Unsupervised Data Augmentation for Consistency Training

Qizhe Xie, Zihang Dai, E. Hovy, Minh-Thang Luong, Quoc V. Le
Computer Science, Mathematics
29 April 2019

We propose a method to apply data augmentation to unlabeled data in a semi-supervised learning setting that outperforms the state-of-the-art. Expand

Massive Exploration of Neural Machine Translation Architectures

D. Britz, Anna Goldie, Minh-Thang Luong, Quoc V. Le
Computer Science
EMNLP
11 March 2017

We present a large-scale analysis of the sensitivity of NMT architectures to common hyperparameters. Expand

Unsupervised Data Augmentation

Qizhe Xie, Zihang Dai, E. Hovy, Minh-Thang Luong, Quoc V. Le
Computer Science
ArXiv
29 April 2019

We propose to apply state-of-the-art data augmentation methods found in supervised learning as the perturbation function in a semi-supervised learning setting. Expand

Semi-Supervised Sequence Modeling with Cross-View Training

Kevin Clark, Minh-Thang Luong, Christopher D. Manning, Quoc V. Le
Computer Science
EMNLP
22 September 2018

We propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data. Expand

Towards a Human-like Open-Domain Chatbot

D. Adiwardana, Minh-Thang Luong, +8 authors Quoc V. Le
Computer Science, Mathematics
ArXiv
27 January 2020

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. Expand

Recommended Authors