Machine Translation of the Ural-altaic as an Agglutinative Language

In this paper we present the results of Korean to Japanese translation in especial from the machine translation system between Korean and Japanese language which have linguistic properties and similarities strongly in Syntax or Phraseology as the Ural-Altaic languages. For its implementation, we have developed syntax based machine translation system KANT designed to be capable of multi-lingual translation. But, despite the advantageous linguistic facts between both languages as the typical agglutinative languages there are many complicated problems to solve for Korean to Japanese machine translation. So, in order to survey these problems more sufficiently and to make strong merits of almost same sentence structure more efficient for machine translation, the KANT/ KJ system was designed to expand easily the range of syntactic limitation for word sensing and to improve the functions for semantic analysis.