K
Kyunghyun Cho
Researcher at New York University
Publications - 351
Citations - 116609
Kyunghyun Cho is an academic researcher from New York University. The author has contributed to research in topics: Machine translation & Recurrent neural network. The author has an hindex of 77, co-authored 316 publications receiving 94919 citations. Previous affiliations of Kyunghyun Cho include Facebook & Université de Montréal.
Papers
More filters
Proceedings ArticleDOI
Joint Event Extraction via Recurrent Neural Networks
TL;DR: This work proposes to do event extraction in a joint framework with bidirectional recurrent neural networks, thereby benefiting from the advantages of the two models as well as addressing issues inherent in the existing approaches.
Proceedings ArticleDOI
Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
TL;DR: This article proposed a multi-way, multilingual NMT model with a single attention mechanism that is shared across all language pairs and observed that the proposed model significantly improves the translation quality of low-resource language pairs.
Proceedings ArticleDOI
Learning distributed representations of sentences from unlabelled data
TL;DR: In this article, a systematic comparison of models that learn distributed representations of words from unlabeled data is presented, and it is shown that shallow log-linear models work best for building representation spaces that can be decoded with simple spatial distance metrics.
Posted Content
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
TL;DR: This paper proposes a new approach to second-order optimization, the saddle-free Newton method, that can rapidly escape high dimensional saddle points, unlike gradient descent and quasi-Newton methods, and applies this algorithm to deep or recurrent neural network training, and provides numerical evidence for its superior optimization performance.
Proceedings Article
On the Number of Linear Regions of Deep Neural Networks
TL;DR: In this article, the authors study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions that they have.