One of the most popular approaches for neural network compression is sparsification — learning sparse weight matrices. In structured sparsification, weights are set to zero by groups corresponding to structure units, e. g. neurons. We further develop the structured sparsification approach for the gated recurrent neural networks, e. g. Long Short-Term Memory (LSTM). Specifically, in addition to the sparsification of individual weights and neurons, we propose sparsifying the preactivations of gates. This makes some gates constant and simplifies an LSTM structure. We test our approach on the text classification and language modeling tasks. Our method improves the neuron-wise compression of the model in most of the tasks. We also observe that the resulting structure of gate sparsity depends on the task and connect the learned structures to the specifics of the particular tasks.
A survey on the application of recurrent neural networks to statistical language modeling
