Pruning sparse non-negative matrix n-gram language models
Joris Pelemans, Noam Shazeer, Ciprian I. Chelba · 2015
Copyright © 2015 ISCA. In this paper we present a pruning algorithm and experimental results for our recently proposed Sparse Non-negative Matrix (SNM) family of language models (LMs). We show that when trained with only n-gram features SNMLM pruning based on a mutual information criterion yields the best known pruned model on the One Billion Word Language Model Benchmark, reducing perplexity with 18% and 57% over Katz and Kneser- Ney LMs, respectively. We also present a method for converting an SNMLM to ARPA back-off format which can be readily used in a single-pass decoder for Automatic Speech Recognition.