no code implementations • 26 Mar 2024 • Nicolas Guerin, Shane Steinert-Threlkeld, Emmanuel Chemla
Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation.
1 code implementation • 18 Feb 2024 • Louis Jalouzot, Robin Sobczyk, Bastien Lhopitallier, Jeanne Salle, Nur Lan, Emmanuel Chemla, Yair Lakretz
Together, this demonstrates the utility of Metric-Learning Encoding Methods for studying how linguistic features are neurally encoded in language models and the advantage of MLEMs over traditional methods.
1 code implementation • 15 Feb 2024 • Nur Lan, Emmanuel Chemla, Roni Katzir
Neural networks offer good approximation to many tasks but consistently fail to reach perfect generalization, even when theoretical work shows that such perfect solutions can be expressed by certain architectures.
1 code implementation • 11 Nov 2023 • Matan Abudy, Nur Lan, Emmanuel Chemla, Roni Katzir
Associative memory architectures are designed for memorization but also offer, through their retrieval method, a form of generalization to unseen inputs: stored memories can be seen as prototypes from this point of view.
1 code implementation • 16 Aug 2023 • Nur Lan, Emmanuel Chemla, Roni Katzir
How well do neural networks generalize?
1 code implementation • 31 Oct 2021 • Nur Lan, Michal Geyer, Emmanuel Chemla, Roni Katzir
We train neural networks to optimize a Minimum Description Length score, i. e., to balance between the complexity of the network and its accuracy at a task.
1 code implementation • ACL 2020 • Nur Geffen Lan, Emmanuel Chemla, Shane Steinert-Threlkeld
We propose a general framework to study language emergence through signaling games with neural agents.