An intelligent full-text Chinese-English translation system

Abstract Machine translation has traditionally been regarded by many as the field of study of linguists and natural language processing researchers. This paper attempted to offer an alternative, non-traditional approach to turn machine translation concepts into creation and reality. It has been recognized that machine translation of Chinese is an extremely difficult task. This paper introduced the CITAC technology for the design of intelligent full-text Chinese–English translation machines. The core of the CITAC technology is the central intelligence unit (CIU) which facilitates the design. The CIU grows with experience. Parsing of Chinese sentences is based on the trio-segmentation technique. The difficulties caused by cultural differences between Chinese and English have been overcome by the linguistic canonical form (LCF) transformation and the information pattern (IP) approach. Self-correction of grammatical errors is handled by the grammar marker pattern (GMP) approach. The innovative design concepts have been successfully developed and implemented in a commercial machine known as the CITAC translator which is a PC-based software system. For more information, please visit the CITAC home page at www.citac-MT.com