Research on the Mongolian words conversion from minimum word element code to international standard code based on hidden Markov model

摘要

In this paper, we mainly study the Mongolian words conversion from minimum word element code to International Standard Coding based on hidden markov model. The main contents of the study is that obtain state matrix and the transmission matrix of hidden Markov model based on the training corpus and use Viterbi algorithm to implement coding conversion. The experiment has achieved good results that the average accuracy of the closed system is 91.32% and the accuracy of the open system is 91.48%.