Rule base combined linguistics knowledge with corpus

This paper proposes a new approach to construction of rule bases for the transferred-based machine translation. In our approach, the rule bases are constructed in combination of the linguistics knowledge and large scale of corpora. On the one hand, the lexical knowledge, the syntactic knowledge and the semantic knowledge are all used in the rules. On the other hand, the knowledge is used for the statistics and self-learning rules. In each rule base, all rules are scored and ranked. Thus, an impersonal choice for the sentence can be made. The preliminary experimental results show that the approach may increase the speed to build the rule base and improve the quality of rules.