Victor H. Yngve

Abstract

Victor Yngve (5 July 1920 to 15 January 2012) was a major contributor in a number of fields within computational linguistics: as the leading researcher in machine translation (MT) at the Massachusetts Institute of Technology (MIT), as editor of its first journal, as designer and developer of the first non-numerical programming language (COMIT), and as an influential contributor to linguistic theory. While still completing his Ph.D. on cosmic ray physics at the University of Chicago during 1950–1953, Yngve had an idea for using the newly invented computers to translate languages. He contemplated building a translation machine based on simple dictionary lookup. At this time he knew nothing of the earlier speculations of Warren Weaver and others (Hutchins 1997). Then during a visit to Claude Shannon at Bell Telephone Laboratories in early 1952 he heard about a conference on machine translation to be held at MIT in June of that year. He attended the opening public meeting and participated in conference discussions, and then, after Bar-Hillel’s departure from MIT, he was appointed in July 1953 by Jerome Wiesner at the Research Laboratory for Electronics (RLE) to lead the MT research effort there. (For a retrospective survey of his MT research activities see Yngve [2000].) Yngve, along with many others at the time, deprecated the premature publicity around the Georgetown–IBM system demonstrated in January 1954. Yngve was appalled to see research of such a limited nature reported in newspapers; his background in physics required experiments to be carefully planned, with their assumptions made plain, and properly tested and reviewed by other researchers. He was determined to set the new field of MT on a proper scientific course. The first step was a journal for the field, to be named Mechanical Translation—the field became “machine translation” in later years. He found a collaborator for the journal in William N. Locke of the MIT Modern Languages department. The aim was to provide a forum for information about what research was going on in the form of abstracts, and then for peer-reviewed articles. The first issue appeared in March 1954. Yngve’s first experiments at MIT in October 1953 were an implementation of his earlier ideas on word-for-word translation. The results of translating fromGermanwere published in the collection edited by Locke and Booth (Yngve 1955b). One example of output began: