English

On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation

Computation and Language 2016-02-26 v3

Abstract

We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It is shown that NCE-trained bi-directional NNLM outperformed the one trained by conventional maximum likelihood training. But still(regretfully), it did not out-perform the baseline uni-directional NNLM.

Keywords

Cite

@article{arxiv.1602.06064,
  title  = {On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation},
  author = {Tianxing He and Yu Zhang and Jasha Droppo and Kai Yu},
  journal= {arXiv preprint arXiv:1602.06064},
  year   = {2016}
}
R2 v1 2026-06-22T12:53:34.824Z