Aggregate and mixed-order Markov models for statistical language processing
Abstract
We consider the use of language models whose size and accuracy are intermediate between different order n-gram models. Two types of models are studied in particular. Aggregate Markov models are class-based bigram models in which the mapping from words to classes is probabilistic. Mixed-order Markov models combine bigram models whose predictions are conditioned on different words. Both types of models are trained by Expectation-Maximization (EM) algorithms for maximum likelihood estimation. We examine smoothing procedures in which these models are interposed between different order n-grams. This is found to significantly reduce the perplexity of unseen word combinations.
Cite
@article{arxiv.cmp-lg/9706007,
title = {Aggregate and mixed-order Markov models for statistical language processing},
author = {Lawrence Saul and Fernando Pereira},
journal= {arXiv preprint arXiv:cmp-lg/9706007},
year = {2008}
}
Comments
9 pages, 4 PostScript figures, uses psfig.sty and aclap.sty; to appear in the proceedings of EMNLP-2