This paper proposes an Approximate n-gram Markov Model for bag generation. Directed word association pairs with distances are used to approximate (n-1)-gram and n-gram training tables. This model has parameters of word association model, and merits of both word association model and Markov Model. The training knowledge for bag generation can be also applied to lexical selection in machine translation design.
@article{arxiv.cmp-lg/9408012,
title = {Approximate N-Gram Markov Model for Natural Language Generation},
author = {Hsin-Hsi Chen and Yue-Shi Lee},
journal= {arXiv preprint arXiv:cmp-lg/9408012},
year = {2008}
}
Comments
to appear in proceedings of QUALICO-94, 6 pages, uuencoded compressed Postscript file; extract with Unix uudecode and uncompress