Machine Translation, i.e., translating one kind of natural language to another kind of natural language by using a computer system, is a very important research branch in Artificial Intelligence. Yao developed a method of translation that he called ``Lexical-Semantic Driven". In his system he introduced 49 ``relation types" including case relations, event relations, semantic relations, and complex relations. The knowledge graph method is a new kind of method to represent an interlingua between natural languages. In this paper, we will give a comparison of these two methods. We will translate one Chinese sentence cited in Yao’s book by using these two methods. Finally, we will use the relations in knowledge graph theory to represent the ``relations" in Lexical-Semantic Driven, and partition the relations in Lexical-Semantic Driven into groups according to the relations in knowledge graph theory.
|Publisher||Department of Applied Mathematics, University of Twente|
Liu, X., & Hoede, C. (2002). On Yao's method of translation
. (Memorandum; No. 1662). Enschede: University of Twente, Department of Applied Mathematics.