Variational Bi-LSTMs

@article{Shabanian2017VariationalB,
  title={Variational Bi-LSTMs},
  author={Samira Shabanian and Devansh Arpit and Adam Trischler and Yoshua Bengio},
  journal={CoRR},
  year={2017},
  volume={abs/1711.05717}
}
Recurrent neural networks like long short-term memory (LSTM) are important architectures for sequential prediction tasks. LSTMs (and RNNs in general) model sequences along the forward time direction. Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are generally known to perform better at such tasks because they capture a richer representation of the data. In the training of Bi-LSTMs, the forward and backward paths are learned… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 80 times over the past 90 days. VIEW TWEETS
4 Citations
36 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 36 references

Similar Papers

Loading similar papers…