Deep neural networks and humans both benefit from compositional language structure
Abstract Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more compositional and transparent structures are typically...
Saved in:
| Main Authors: | Lukas Galke, Yoav Ram, Limor Raviv |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55158-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
No evidence for generational differences in the conventionalisation of face emojis
by: Vera Kempe, et al.
Published: (2025-08-01) -
Human Activity Recognition Using Graph Structures and Deep Neural Networks
by: Abed Al Raoof K. Bsoul
Published: (2024-12-01) -
Using recurrent neural network to estimate irreducible stochasticity in human choice behavior
by: Yoav Ger, et al.
Published: (2024-09-01) -
Deepfake Audio Detection for Urdu Language Using Deep Neural Networks
by: Omair Ahmad, et al.
Published: (2025-01-01) -
Optimisation of material composition in functionally graded plates using a structure-tuned deep neural network
by: Ryoichi Chiba, et al.
Published: (2024-12-01)