1 code implementation • 1 Dec 2021 • Tomasz Korbak, Hady Elsahar, German Kruszewski, Marc Dymetman
Machine learning is shifting towards general-purpose pretrained generative models, trained in a self-supervised manner on large amounts of data, which can then be applied to solve a large number of tasks.
1 code implementation • NAACL 2019 • Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, Marco Baroni
Importantly, the behaviour of these units is partially controlled by other units independently shown to track syntactic structure.
no code implementations • ACL 2018 • Alexis Conneau, German Kruszewski, Guillaume Lample, Lo{\"\i}c Barrault, Marco Baroni
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing.
no code implementations • 20 May 2018 • Dieuwke Hupkes, Anand Singh, Kris Korrel, German Kruszewski, Elia Bruni
While neural network models have been successfully applied to domains that require substantial generalisation skills, recent studies have implied that they struggle when solving the task they are trained on requires inferring its underlying compositional structure.
6 code implementations • 3 May 2018 • Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, Marco Baroni
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing.
no code implementations • TACL 2015 • German Kruszewski, Denis Paperno, Marco Baroni
Corpus-based distributional semantic models capture degrees of semantic relatedness among the words of very large vocabularies, but have problems with logical phenomena such as entailment, that are instead elegantly handled by model-theoretic approaches, which, in turn, do not scale up.