SOTAVerified

Exploring the Limits of Language Modeling

2016-02-07Code Available1· sign in to hype

Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, Yonghui Wu

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language. We perform an exhaustive study on techniques such as character Convolutional Neural Networks or Long-Short Term Memory, on the One Billion Word Benchmark. Our best single model significantly improves state-of-the-art perplexity from 51.3 down to 30.0 (whilst reducing the number of parameters by a factor of 20), while an ensemble of models sets a new record by improving perplexity from 41.0 down to 23.7. We also release these models for the NLP and ML community to study and improve upon.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
One Billion Word10 LSTM+CNN inputs + SNM10-SKIP (ensemble)PPL23.7Unverified
One Billion WordLSTM-8192-1024 + CNN InputPPL30Unverified
One Billion WordLSTM-8192-1024PPL30.6Unverified

Reproductions