• Publications
  • Influence
OpenNMT: Open-Source Toolkit for Neural Machine Translation
TLDR
The toolkit prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. Expand
Bottom-Up Abstractive Summarization
TLDR
This work explores the use of data-efficient content selectors to over-determine phrases in a source document that should be part of the summary, and shows that this approach improves the ability to compress text, while still generating fluent summaries. Expand
Image-to-Markup Generation with Coarse-to-Fine Attention
TLDR
This work presents a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism that outperforms classical mathematical OCR systems by a large margin on in-domain rendered data and also performs well on out-of-domain handwritten data. Expand
What You Get Is What You See: A Visual Markup Decompiler
TLDR
A general-purpose, deep learning-based system to decompile an image into presentational markup that employs a convolutional network for text and layout recognition in tandem with an attention-based neural machine translation system. Expand
Neural Linguistic Steganography
TLDR
This work proposes a steganography technique based on arithmetic coding with large-scale neural language models that can generate realistic looking cover sentences as evaluated by humans, while at the same time preserving security by matching the cover message distribution with the language model distribution. Expand
Diversifying Restricted Boltzmann Machine for Document Modeling
TLDR
Diversified RBM (DRBM) is proposed which diversifies the hidden units, to make them cover not only the dominant topics, but also those in the long-tail region, and it is proved that maximizing the lower bound with projected gradient ascent can increase this diversity metric. Expand
Latent Alignment and Variational Attention
TLDR
Variational attention networks are considered, alternatives to soft and hard attention for learning latent variable alignment models, with tighter approximation bounds based on amortized variational inference, and methods for reducing the variance of gradients are proposed to make these approaches computationally feasible. Expand
OpenNMT: Neural Machine Translation Toolkit
TLDR
The system prioritizes efficiency, modularity, and extensibility with the goal of supporting NMT research into model architectures, feature representations, and source modalities, while maintaining competitive performance and reasonable training requirements. Expand
On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
TLDR
This paper analyzes how the mutual angular regularizer (MAR) affects the generalization performance of supervised LVMs and presents empirical study which demonstrates that the MAR can greatly improve the performance of NN and the empirical observations are in accordance with the theoretical analysis. Expand
Entity Hierarchy Embedding
TLDR
This work proposes a principled framework of embedding entities that integrates hierarchical information from large-scale knowledge bases and shows that both the entity vectors and category distance metrics encode meaningful semantics. Expand
...
1
2
3
...