One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling

11 Dec 2013Ciprian Chelba • Tomas Mikolov • Mike Schuster • Qi Ge • Thorsten Brants • Phillipp Koehn • Tony Robinson

We propose a new benchmark corpus to be used for measuring progress in statistical language modeling. With almost one billion words of training data, we hope this benchmark will be useful to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques. We show performance of several well-known types of language models, with the best results achieved with a recurrent neural network based language model.

Full paper


Task Dataset Model Metric name Metric value Global rank Compare
Language Modelling One Billion Word RNN-1024 + 9 Gram PPL 51.3 # 14
Language Modelling One Billion Word RNN-1024 + 9 Gram Number of params 20B # 14