2003
Yoshua Bengio
b. 1964
Language & Representation
Advanced neural language models and attention; shared the 2018 Turing Award with Hinton and LeCun.
His 2003 neural probabilistic language model introduced learned word embeddings.
His lab developed attention for translation in 2014, a direct precursor to the Transformer. He is now a leading voice on AI safety.
Dated contributions
2003
Language & Representation
Yoshua Bengio
Advanced neural language models and attention; shared the 2018 Turing Award with Hinton and LeCun.
Paper · 2003 — A Neural Probabilistic Language Model ↗
