Sliced Recurrent Neural Networks
Zeping
Yu
author
Gongshen
Liu
author
2018-08
text
Proceedings of the 27th International Conference on Computational Linguistics
Association for Computational Linguistics
Santa Fe, New Mexico, USA
conference publication
Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time to train RNNs. In this paper, we introduce sliced recurrent neural networks (SRNNs), which could be parallelized by slicing the sequences into many subsequences. SRNNs have the ability to obtain high-level information through multiple layers with few extra parameters. We prove that the standard RNN is a special case of the SRNN when we use linear activation functions. Without changing the recurrent units, SRNNs are 136 times as fast as standard RNNs and could be even faster when we train longer sequences. Experiments on six large-scale sentiment analysis datasets show that SRNNs achieve better performance than standard RNNs.
yu-liu-2018-sliced
https://aclanthology.org/C18-1250
2018-08
2953
2964