We present a novel approach for continuous space language models in statistical machine translation by using Restricted Boltzmann Machines (RBMs). The probability of an n-gram is calculated by the free energy of the RBM instead of a feedforward neural net. Therefore, the calculation is much faster and can be integrated into the translation process instead of using the language model only in a re-ranking step. Furthermore, it is straightforward to introduce additional word factors into the language model. We observed a faster convergence in training if we include automatically generated word classes as an additional word factor. We evaluated the RBM-based language model on the German to English and English to French translation task of TED lectures. Instead of replacing the conventional n-grambased language model, we trained the RBM-based language model on the more important but smaller in-domain data and combined them in a log-linear way. With this approach we could show improvements of about half a BLEU point on the translation task.
Cite as: Niehues, J., Waibel, A. (2012) Continuous space language models using restricted Boltzmann machines. Proc. International Workshop on Spoken Language Translation (IWSLT 2012), 164-170
@inproceedings{niehues12_iwslt,
author={Jan Niehues and Alex Waibel},
title={{Continuous space language models using restricted Boltzmann machines}},
year=2012,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2012)},
pages={164--170}
}