A Quantitative Study on the Senses Distribution Characteristics of the Mongolian Word "xar_a (ᠬᠠᠷᠠ)"

In the Mongolian language, polysemous words are ubiquitous. The recognition of polysemous words is a difficult problem in all stages of Mongolian information processing because of the large number of polysemous words, the complexity of morphological changes and the diversity of ideographic forms. This paper takes the word "xar_a (ᠬᠠᠷ᠎ᠠ)" with 12 senses in the Mongolian Dictionary as the research object, and makes a statistical analysis of the distribution of the senses of the word "xar_a (ᠬᠠᠷ᠎ᠠ)" in the "one million word level modern Mongolian corpus", and then makes a quantitative analysis of the characteristics and laws of the distribution of the senses of the word "xar_a (ᠬᠠᠷ᠎ᠠ)" in Mongolian. The results show that the distribution of the senses of the word "xar_a (ᠬᠠᠷ᠎ᠠ)" in Mongolian is uneven in the corpus, and the distribution of the senses of the word "xar_a (ᠬᠠᠷ᠎ᠠ)" conforms to the Right truncated modified Zipf-Alekseev distribution model. This study provides an example for the tracking study of the characteristics and laws of Mongolian polysemy, and has great reference value for future research fields such as automatic proofreading, dictionary compilation, language teaching, machine translation, information retrieval and so on.