Proofreader of Mongolian Vocabulary Based on Language Model of Syllabic Statistics

Abstract

Mongolian script proofreading is delicate but monotonous work, which is for long done by hand. This paper is attempted to build up a Mongolian text proofreading system based on language model of syllabic statistics by decomposing a Mongolian word into syllables before putting them into the model. In the light of lexical features of Mongolian, this paper ushers some exploratory work in automatic proofreading of Mongolian vocabulary