Slim Embedding Layers for Recurrent Neural Language Models
This addresses storage bottlenecks for users of recurrent neural language models, though it is incremental as it builds on existing methods with a compression technique.
The paper tackles the problem of large parameter storage in recurrent neural language models with large vocabularies by introducing a space compression method that randomly shares structured parameters in embedding layers, achieving similar perplexity and BLEU scores while using a very tiny fraction of parameters.
Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models. In this paper, we introduce a simple space compression method that randomly shares the structured parameters at both the input and output embedding layers of the recurrent neural language models to significantly reduce the size of model parameters, but still compactly represent the original input and output embedding layers. The method is easy to implement and tune. Experiments on several data sets show that the new method can get similar perplexity and BLEU score results while only using a very tiny fraction of parameters.