AUTOMATING KNOWLEDGE ACQUISITION FOR MACHINE TRANSLATION

Machine translation of human languages (for example, Japanese, English , Spanish) was one of the earliest goals of computer science research, and it remains an elusive one. Like many Al tasks, translation requir es an immense amount of knowledge about language and the world. Recent approaches to machine translation frequently make use of text-based l earning algorithms to fully or partially automate the acquisition of k nowledge. This article illustrates these approaches.