Mongolian Morphological Segmentation with Hidden Markov Model

Morphological segmentation breaks words into morphemes. It is an important issue in natural language processing systems. The paper proposes a morphological segmentation method with hidden markov model method for Mongolian. The method uses sentences which consist of Mongolian words associated with affix sequences to establish a Hidden Markov Model. We identify Mongolian affix in a given word based on this model. When a morpheme is identified as the affix, we can get the stem easily according to Mongolian word and affix. The segmentation error is corrected by applying the vocabulary model of words and affixes, the 1-gram model of affixes and the reverse maximum matching model. In order to further validate the effectiveness and practicality of the proposed method, we use morphemes as pivot language in a chained machine translation system. Experiments show that the precision of the morphological segmentation system achieves 96.24%, and the translation results of the statistical machine translation system is improved significantly.