Abstract: The development of Mongolian language information is slow due to lack of electronic text data and massive difficulty of language analysis. In order to solve the problem mentioned above, a cross language retrieval model oriented to Mongolian natural disaster information was constructed by using Semantic Web ontology technology. Model test results show that this model can achieve a better cross language retrieval effect. At the same time, the cross language retrieval model proposed in this paper has a certain commonality, which can provide reference for similar applications.