Paper: Better Language Models With Model Merging

ACL ID W96-0206
Title Better Language Models With Model Merging
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 1996

This paper investigates model merging, a tech- nique for deriving Markov models from text or speech corpora. Models are derived by starting with a large and specific model and by successi- vely combining states to build smaller and more general models. We present methods to reduce the time complexity of the algorithm and report on experiments on deriving language models for a speech recognition task. The experiments show the advantage of model merging over the standard bigram approach. The merged model assigns a lower perplexity to the test set and uses consi- derably fewer states.