English

Exploring the Limits of Language Modeling

Computation and Language 2016-02-15 v2

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.

Keywords

Cite

@article{arxiv.1602.02410,
  title  = {Exploring the Limits of Language Modeling},
  author = {Rafal Jozefowicz and Oriol Vinyals and Mike Schuster and Noam Shazeer and Yonghui Wu},
  journal= {arXiv preprint arXiv:1602.02410},
  year   = {2016}
}
R2 v1 2026-06-22T12:45:02.435Z