Four Generations of Machine Translation Research and Prospects for the Future

Abstract

This paper begins with a description of four generations of research in machine translation: the original efforts of 1957 to 1965 and three types of surviving and sometimes competing present projects. The three types of present projects include those relying on "brute force" methods involving larger and faster computers; those based on a linguistic tradition which asserts that knowledge required for machine translation can be assimilated to the structure of a grammar-based system with a semantic component; and those stemming from artificial intelligence research, with an emphasis on knowledge structures. The paper argues that the artificial intelligence approach has the best chance of simulating the communicative abilities necessary for realistic machine translation and gives an account of how knowledge structures might cope with one of the classic problems of machine translation: that of metaphor, or "semantic boundary breaking." (AA)