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
Posted Content
Breast density classification with deep convolutional neural networks
Nan Wu,Krzysztof J. Geras,Yiqiu Shen,Jingyi Su,S. Gene Kim,Eric Kim,Stacey Wolfson,Linda Moy,Kyunghyun Cho +8 more
TL;DR: In this article, the authors explore the limits of this task with a data set coming from over 200,000 breast cancer screening exams and use this data to train and evaluate a strong convolutional neural network classifier.
Posted Content
First Result on Arabic Neural Machine Translation
TL;DR: It is observed that the neural machine translation significantly outperform the phrase-based system on an out-of-domain test set, making it attractive for real-world deployment.
Posted Content
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search.
Gyuwan Kim,Kyunghyun Cho +1 more
TL;DR: This paper extends PoWER-BERT and proposes Length-Adaptive Transformer, a transformer that can be used for various inference scenarios after one-shot training and demonstrates the superior accuracy-efficiency trade-off under various setups, including span-based question answering and text classification.
Posted Content
Meta-Learning for Low-Resource Neural Machine Translation
TL;DR: This paper proposed a meta-learning approach for low-resource NMT, which uses the universal lexical representation to overcome the input-output mismatch across different languages, and showed that the proposed approach significantly outperforms the multilingual, transfer learning based approach.
Posted Content
Emergent Language in a Multi-Modal, Multi-Step Referential Game.
TL;DR: A novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information exchange is bidirectional and of arbitrary duration is proposed.