Thang Luong

Publications29
h-index10
Citations6,445
Highly Influential Citations739
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • C. Castro
  • 115 Publications, 2,328 Citations
  • Christopher D. Manning
  • 474 Publications, 111,438 Citations
  • Yoshua Bengio
  • 811 Publications, 257,906 Citations
  • R. Socher
  • 193 Publications, 64,788 Citations
  • Publications
  • Influence
Effective Approaches to Attention-based Neural Machine Translation
TLDR
This paper examines two simple and effective classes of attentional mechanism: a global approach which always attends to all source words and a local one that only looks at a subset of source words at a time. Expand
  • 4,444
  • 514
  • PDF
Addressing the Rare Word Problem in Neural Machine Translation
TLDR
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. Expand
  • 595
  • 81
  • PDF
Better Word Representations with Recursive Neural Networks for Morphology
TLDR
We combine recursive neural networks (RNNs), where each morpheme is a basic unit, with neural language models (NLMs) to consider contextual information in learning morphologically complex word representations. Expand
  • 702
  • 61
  • PDF
Bilingual Word Representations with Monolingual Quality in Mind
TLDR
In this work, we propose a joint model to learn word representations from scratch that utilizes both the context coocurrence information through the monolingual component and the meaning equivalent signals from the bilingual constraint. Expand
  • 272
  • 48
  • PDF
When Are Tree Structures Necessary for Deep Learning of Representations?
TLDR
We find that recursive models help mainly on tasks (like semantic relation extraction) that require longdistance connection modeling, particularly on very long sequences. Expand
  • 188
  • 14
  • PDF
Learning Longer-term Dependencies in RNNs with Auxiliary Losses
TLDR
This paper proposes a simple method that improves the ability to capture long term dependencies in RNNs by adding an unsupervised auxiliary loss to the original objective. Expand
  • 76
  • 10
  • PDF
Learning Distributed Representations for Multilingual Text Sequences
TLDR
We propose a novel approach to learning distributed representations of variable-length text sequences in multiple languages simultaneously. Expand
  • 45
  • 6
  • PDF
The More Extreme Nature of North American Monsoon Precipitation in the Southwestern United States as Revealed by a Historical Climatology of Simulated Severe Weather Events
AbstractLong-term changes in North American monsoon (NAM) precipitation intensity in the Southwest U.S. are evaluated through the use of convective-permitting model simulations of objectively… Expand
  • 32
  • 1
  • PDF
Neural Machine Translation
TLDR
Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Expand
  • 12
  • 1
  • PDF
18F-FDG PET/CT appearance of metastatic brachial plexopathy involving epidural space from breast carcinoma.
Patient is a 74-year-old woman with a history of breast carcinoma and known metastatic brachial plexopathy and pulmonary and mediastinal nodal involvement. She had bilateral mastectomies 5 years ago… Expand
  • 9
  • 1