AI

Pruning Sparse Non-negative Matrix N-gram Language Models

Abstract

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 have uncovered a bug in the experimental setup for SNM pruning; see Errata section for correct results.

We also illustrate 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.