CLFeb 19, 2016
On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation
arXiv:1602.06064v38 citations
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for language modeling, addressing training efficiency but with limited practical impact.
The authors tackled training a bi-directional neural network language model using noise contrastive estimation, finding it outperformed maximum likelihood training but did not surpass a baseline uni-directional model on the PTB dataset.
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.