English

Bayesian Compression for Natural Language Processing

Computation and Language 2018-12-13 v2 Machine Learning Machine Learning

Abstract

In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer, which size grows proportionally to the vocabulary length. We propose a Bayesian sparsification technique for RNNs which allows compressing the RNN dozens or hundreds of times without time-consuming hyperparameters tuning. We also generalize the model for vocabulary sparsification to filter out unnecessary words and compress the RNN even further. We show that the choice of the kept words is interpretable. Code is available on github: https://github.com/tipt0p/SparseBayesianRNN

Keywords

Cite

@article{arxiv.1810.10927,
  title  = {Bayesian Compression for Natural Language Processing},
  author = {Nadezhda Chirkova and Ekaterina Lobacheva and Dmitry Vetrov},
  journal= {arXiv preprint arXiv:1810.10927},
  year   = {2018}
}

Comments

Published in EMNLP 2018