Mechanisms for handling nested dependencies in neural-network language models and humans

Recursive processing in sentence comprehension is considered a hallmark of human linguistic abilities. However, its underlying neural mechanisms remain largely unknown. We studied whether a modern artificial neural network trained with “deep learning” methods mimics a central aspect of human sentenc...

Full description

Bibliographic Details
Main Authors:	Baroni, M. (Author), Dehaene, S. (Author), Hupkes, D. (Author), Lakretz, Y. (Author), Marelli, M. (Author), Vergallito, A. (Author)
Format:	Article
Language:	English
Published:	Elsevier B.V. 2021
Subjects:	article comprehension Comprehension deep learning embedding female gender Grammatical agreement human human experiment Humans language Language Language models linguistics Linguistics Long-range dependencies male Memory, Short-Term Neural Networks, Computer prediction recurrent neural network Recurrent neural networks Recursion Relative clauses short term memory simulation Syntactic processing systematic error working memory
Online Access:	View Fulltext in Publisher

Internet

View Fulltext in Publisher

Mechanisms for handling nested dependencies in neural-network language models and humans

Internet

Similar Items