A Combination of Statistical and Rule-Based Approach for Mongolian Lexical Analysis

Mongolian lexical analysis is the first step in Mongolian information processing such as Chinese-Mongolian machine translation. In this paper, we introduce a statistic and rule based approach to solving the Mongolian word segmentation & POS tagging all at once. In this method, we use tree frame as basic statistical model. And then we combine the model with some rules to improve the lexical analysis system accuracy. The experiment results show that the word-level accuracy of joint segmentation and POS tagging is 95.2%, stem / postfix-level accuracy is 94.6%.