Diane Bouchacourt

Diane is a research scientist at Facebook AI Research (FAIR), focusing on probabilistic models for representation learning and unsupervised/weakly supervised learning. She also analyzes communication protocols of artificial neural agents and builds interpretable/explainable models and representations. Diane earned her Ph.D. in machine learning at the University of Oxford.

Diane's Publications

April 07, 2020

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,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances

Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution. We propose here a new task capturing crucial aspects of the human environment,…

Diane Bouchacourt, Marco Baroni,

April 07, 2020

April 07, 2020

RESEARCH

COMPUTER VISION

How agents see things: On visual representations in an emergent language game

There is growing interest in the language developed by agents interacting in emergent-communication settings. Earlier studies have focused on the agents’ symbol usage, rather than on their representation of visual input. In this paper, we…

Diane Bouchacourt, Marco Baroni,

April 07, 2020