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
-
Human Activity Recognition Using Graph Structures and Deep Neural Networks
by: Abed Al Raoof K. Bsoul
Published: (2024-12-01) -
Optimisation of material composition in functionally graded plates using a structure-tuned deep neural network
by: Ryoichi Chiba, et al.
Published: (2024-12-01) -
Popular Song Composition Based on Deep Learning and Neural Network
by: Jun Kuang, et al.
Published: (2021-01-01) -
Compositional-structural, semantic and presuppositional-pragmatic parameters and defects of generated short texts in the GigaChat language neural network
by: S. V. Gusarenko, et al.
Published: (2024-09-01) -
Stochastic Stability of Neural Networks with Both Markovian Jump Parameters and Continuously Distributed Delays
by: Quanxin Zhu, et al.
Published: (2009-01-01)