ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Can artificial neural networks learn language models?

Wei Xu, Alex Rudnicky

Currently, N-gram models are the most common and widely used models for statistical language modeling. In this paper, we investigated an alternative way to build language models, i.e., using artificial neural networks to learn the language model. Our experiment result shows that the neural network can learn a language model that has performance even better than standard statistical methods.


Cite as: Xu, W., Rudnicky, A. (2000) Can artificial neural networks learn language models? Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 202-205

@inproceedings{xu00b_icslp,
  author={Wei Xu and Alex Rudnicky},
  title={{Can artificial neural networks learn language models?}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 1, 202-205}
}