One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
This provides a large-scale benchmark for evaluating language modeling techniques, though it is incremental as it builds on existing methods.
The authors introduced a new benchmark corpus with nearly one billion words to measure progress in statistical language modeling, showing that a combination of techniques reduces perplexity by 35% over a baseline unpruned Kneser-Ney 5-gram model.
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. The baseline unpruned Kneser-Ney 5-gram model achieves perplexity 67.6; a combination of techniques leads to 35% reduction in perplexity, or 10% reduction in cross-entropy (bits), over that baseline. The benchmark is available as a code.google.com project; besides the scripts needed to rebuild the training/held-out data, it also makes available log-probability values for each word in each of ten held-out data sets, for each of the baseline n-gram models.