Efficient language model look-ahead probabilities generation using lower order LM look-ahead information

Abstract

In this paper, an efficient method for language model lookahead probability generation is presented. Traditional methods generate language model look-ahead (LMLA) probabilities for each node in the LMLA tree recursively in a bottom to up manner. The new method presented in this paper makes use of the sparseness of the n-gram model and starts the process of generating an n-gram LMLA tree from a backoff LMLA tree. Only a small number of nodes are updated with explicitly estimated LM probabilities. This speeds up the bigram and trigram LMLA tree generation by a factor of 3 and 12 respectively.