Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models

Recurrent neural network language models (RNNLM) form a valuable foundation for many NLP systems, but training the models can be computationally expensive, and may take days to train on a large corpus. We explore a technique that uses large corpus n-gram statistics as a regularizer for training a neural network LM on a smaller corpus. In experiments with the Billion-Word andWikitext corpora, we show that the technique is effective, and more time-efficient than simply training on a larger sequential corpus. We also introduce new strategies for selecting the most informative n-grams, and show that these boost efficiency.