Diane Bouchacourt

Diane is a research scientist at Facebook AI Research (FAIR), focusing on representation learning and unsupervised/weakly supervised learning. She is interested in building robust models by using group theory and disentanglement methods. Diane earned her Ph.D. in machine learning at the University of Oxford.

Diane's Publications

October 12, 2020

RESEARCH

Permutation Equivariant Models for Compositional Generalization in Language

Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of…

Jonathan Gordon, David Lopez-Paz, Marco Baroni, Diane Bouchacourt

October 12, 2020

October 12, 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,

October 12, 2020

October 12, 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,

October 12, 2020