Linguistic generalization and compositionality in modern artificial neural networks
M Baroni - … Transactions of the Royal Society B, 2020 - royalsocietypublishing.org
In the last decade, deep artificial neural networks have achieved astounding performance in
many natural language-processing tasks. Given the high productivity of language, these …
many natural language-processing tasks. Given the high productivity of language, these …
Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks
Humans can understand and produce new utterances effortlessly, thanks to their
compositional skills. Once a person learns the meaning of a new verb" dax," he or she can …
compositional skills. Once a person learns the meaning of a new verb" dax," he or she can …
Compositionality and generalization in emergent languages
R Chaabouni, E Kharitonov, D Bouchacourt… - arXiv preprint arXiv …, 2020 - arxiv.org
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 …
denoting their parts according to systematic rules, a property known as\emph …
Rearranging the familiar: Testing compositional generalization in recurrent networks
Systematic compositionality is the ability to recombine meaningful units with regular and
predictable outcomes, and it's seen as key to humans' capacity for generalization in …
predictable outcomes, and it's seen as key to humans' capacity for generalization in …
Compositional generalization for primitive substitutions
Compositional generalization is a basic mechanism in human language learning, but
current neural networks lack such ability. In this paper, we conduct fundamental research for …
current neural networks lack such ability. In this paper, we conduct fundamental research for …
Word predictability and semantic similarity show distinct patterns of brain activity during language comprehension
SL Frank, RM Willems - Language, Cognition and Neuroscience, 2017 - Taylor & Francis
We investigate the effects of two types of relationship between the words of a sentence or
text–predictability and semantic similarity–by reanalysing electroencephalography (EEG) …
text–predictability and semantic similarity–by reanalysing electroencephalography (EEG) …
Jump to better conclusions: SCAN both left and right
Lake and Baroni (2018) recently introduced the SCAN data set, which consists of simple
commands paired with action sequences and is intended to test the strong generalization …
commands paired with action sequences and is intended to test the strong generalization …
Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks
Humans can understand and produce new utterances effortlessly, thanks to their systematic
compositional skills. Once a person learns the meaning of a new verb" dax," he or she can …
compositional skills. Once a person learns the meaning of a new verb" dax," he or she can …
Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Systematic compositionality is an essential mechanism in human language, allowing the
recombination of known parts to create novel expressions. However, existing neural models …
recombination of known parts to create novel expressions. However, existing neural models …
Iterated learning for emergent systematicity in vqa
Although neural module networks have an architectural bias towards compositionality, they
require gold standard layouts to generalize systematically in practice. When instead learning …
require gold standard layouts to generalize systematically in practice. When instead learning …