Eugene Kharitonov

Eugene Kharitonov is a Research Engineer, working with the Facebook AI Research team. He earned his PhD in Computer Science from the University of Glasgow. As an undergraduate, Eugene studied Applied Physics and Mathematics at Moscow Institute of Physics and Technology. His current focus is on studying properties of discrete representations and artificial languages that emerge when neural agents communicate with each other.

Eugene's Publications

December 08, 2019

RESEARCH

NLP

Anti-efficient encoding in emergent communication

Despite renewed interest in emergent language simulations with neural networks, little is known about the basic properties of the induced code, and how they compare to human language. One fundamental characteristic of the latter, known as…

Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni

December 08, 2019

November 02, 2019

RESEARCH

NLP

EGG: a toolkit for research on Emergence of lanGuage in Games

There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions about…

Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni

November 02, 2019

July 29, 2019

RESEARCH

NLP

Word-order biases in deep-agent emergent communication

Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such…

Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni

July 29, 2019