activity
20192021
collaborators

8 papers

cs.CL2021

Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov

Despite their practical success, modern seq2seq architectures are unable to generalize systematically on several SCAN tasks. Hence, it is not clear if SCAN-style compositional gene…

cs.CL2020

"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently

Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux

Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a spe…

cs.CL2020

What they do when in doubt: a study of inductive biases in seq2seq learners

Eugene Kharitonov, Rahma Chaabouni

Sequence-to-sequence (seq2seq) learners are widely used, but we still have only limited knowledge about what inductive biases shape the way they generalize. We address that by inve…

cs.CL2020

Compositionality and Generalization in Emergent Languages

Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt +2

Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositional…

cs.CL2019

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

Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt +1

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-enabl…

cs.CL2019

Word-order biases in deep-agent emergent communication

Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric +2

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…