Pith. sign in

REVIEW 1 cited by

Bayesian Compression for Natural Language Processing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.10927 v2 pith:KFMFPL27 submitted 2018-10-25 cs.CL cs.LGstat.ML

classification cs.CLcs.LGstat.ML
keywords bayesiangithublanguagenaturalparametersprocessingsparsificationvocabulary
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Restricted Recurrent Neural Networks

    cs.CL 2019-08 conditional novelty 5.0 of 10

    Partial sharing of input and hidden-state weights in RNN, LSTM, and GRU yields about 50% parameter reduction with roughly unchanged perplexity on two language-modeling benchmarks.

Pith tools