Can recurrent neural networks learn natural language grammars?

@article{Lawrence1996CanRN,
  title={Can recurrent neural networks learn natural language grammars?},
  author={S. Lawrence and C. L. Giles and Sandiway Fong},
  journal={Proceedings of International Conference on Neural Networks (ICNN'96)},
  year={1996},
  volume={4},
  pages={1853-1858 vol.4}
}
Recurrent neural networks are complex parametric dynamic systems that can exhibit a wide range of different behavior. We consider the task of grammatical inference with recurrent neural networks. Specifically, we consider the task of classifying natural language sentences as grammatical or ungrammatical: can a recurrent neural network be made to exhibit the same kind of discriminatory power which is provided by the principles and parameters linguistic framework, or government and binding theory… Expand
20 Citations
A Neural Syntactic Language Model
  • 76
  • PDF
Architectures of neural networks applied for LVCSR language modeling
  • 6
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
  • 451
  • PDF
Perspectives on learning symbolic data with connectionistic systems
  • 10
  • PDF
Targeted Syntactic Evaluation of Language Models
  • 114
  • PDF
Targeted Syntactic Evaluation of Language Models
  • 31
  • PDF
Knowledge Extraction From Trained Neural Networks
  • 12
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 37 REFERENCES
Finite State Automata and Simple Recurrent Networks
  • 491
  • PDF
Distributed Representations, Simple Recurrent Networks, and Grammatical Structure
  • J. L. Elman
  • Mathematics, Computer Science
  • Mach. Learn.
  • 1991
  • 403
  • PDF
Gradient-based learning algorithms for recurrent connectionist networks
  • 81
Three models for the description of language
  • Noam Chomsky
  • Mathematics, Computer Science
  • IRE Trans. Inf. Theory
  • 1956
  • 975
  • PDF
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
  • 3,410
Learning and Applying Contextual Constraints in Sentence Comprehension
  • 282
  • PDF
Induction of Finite-State Languages Using Second-Order Recurrent Networks
  • 213
On the Computational Power of Neural Nets
  • 772
  • Highly Influential
...
1
2
3
4
...