Kyunghyun Cho

E899025

Kyunghyun Cho is a computer scientist and professor known for his influential work in deep learning and neural machine translation, including early contributions to encoder–decoder architectures and attention mechanisms.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label Occurrences
Kyunghyun Cho canonical 2

Statements (45)

Predicate Object
instanceOf computer scientist
researcher
university professor
citizenship South Korea NERFINISHED
coAuthor Bart van Merrienboer NERFINISHED
Dzmitry Bahdanau NERFINISHED
Graham Neubig NERFINISHED
Myle Ott NERFINISHED
Rico Sennrich NERFINISHED
Yoshua Bengio NERFINISHED
educatedAt Aalto University NERFINISHED
employer New York University
fieldOfStudy computer science
fieldOfWork artificial intelligence
deep learning
machine learning
natural language processing
neural machine translation
hasAcademicAdvisor Juha Karhunen NERFINISHED
hasContribution advances in attention-based translation models
development of gated recurrent architectures
popularization of encoder–decoder terminology in NMT
hasHIndex very high in machine learning and NLP research
hasRole principal investigator on research projects
knownFor attention mechanisms in neural networks
early neural machine translation models
encoder–decoder architectures for neural machine translation
gated recurrent unit NERFINISHED
language English
Korean
memberOf New York University Center for Data Science NERFINISHED
notableWork Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling NERFINISHED
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation NERFINISHED
Neural Machine Translation by Jointly Learning to Align and Translate NERFINISHED
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches NERFINISHED
occupation author
professor
scientist
researchInterest multilingual NLP
optimization for deep learning
representation learning
sequence-to-sequence learning
teaches deep learning
natural language processing
workLocation New York City

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.