activity
20162021
most citedThe emergence of number and syntax units in LSTM language models

50 citations · 67 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL20218 cited

Unsupervised and Distributional Detection of Machine-Generated Text

Matthias Gallé, Jos Rozen, Germán Kruszewski +1

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far…

cs.CL2020

Evaluating Online Continual Learning with CALM

Germán Kruszewski, Ionut-Teodor Sorodoc, Tomas Mikolov

Online Continual Learning (OCL) studies learning over a continuous data stream without observing any single example more than once, a setting that is closer to the experience of hu…

cs.CL201950 cited

The emergence of number and syntax units in LSTM language models

Yair Lakretz, German Kruszewski, Theo Desbordes +3

Recent work has shown that LSTMs trained on a generic language modeling objective capture syntax-sensitive generalizations such as long-distance number agreement. We have however n…

cs.CL20194 cited

Cooperative Learning of Disjoint Syntax and Semantics

Serhii Havrylov, Germán Kruszewski, Armand Joulin

There has been considerable attention devoted to models that learn to jointly infer an expression's syntactic structure and its semantics. Yet, \citet{NangiaB18} has recently shown…

cs.CL2018

The Fast and the Flexible: training neural networks to learn to follow instructions from small data

Rezka Leonandya, Elia Bruni, Dieuwke Hupkes +1

Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is…

cs.CL2018

Learning compositionally through attentive guidance

Dieuwke Hupkes, Anand Singh, Kris Korrel +2

While neural network models have been successfully applied to domains that require substantial generalisation skills, recent studies have implied that they struggle when solving th…