Generative Bridging Network for Neural Sequence Prediction

@inproceedings{Chen2018GenerativeBN,
  title={Generative Bridging Network for Neural Sequence Prediction},
  author={Wenhu Chen and Guanlin Li and Shuo Ren and Shujie Liu and Zhirui Zhang and Mu Li and Ming Zhou},
  booktitle={NAACL-HLT},
  year={2018}
}
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional… CONTINUE READING