The Resolution of Lexical Ambiguity in Machine Translation
Dan W. Higinbotham · ScholarsArchive (Brigham Young University) · 1991
In July of 1949, Warren Weaver sent a memorandum to about 30 friends, suggesting the possibility of using computers to translate text from one language into another.This group and their contacts began research in machine translation, and much of the work in natural language processing (and artificial intelligence) has its roots in the early efforts of this group.Weaver's memo began by quoting from a letter he had written: Recognizing fully, even though necessarily vaguely, the semantic difficulties of multiple meanings, etc., I have wondered if it were unthinkable to design a computer which would translate ... (Weaver 1967, p. 190) It was recognized from the very beginning that lexical ambiguity would be one of the major stumbling blocks in processing natural language.1.0 AFrY YEARS OF AMBIGUITY This paper will survey some of the methods used in the last 50 years for automatically resolving lexical ambiguity, and will report on a reasonably effective algorithm combining some of the most successful of those methods. STATISTICAL METHODS