On Whose Shoulders?

Abstract

The title of this piece refers to Newton’s only known modest remark: “If I have seen farther than other men, it was because I was standing on the shoulders of giants.” Since he himself was so much greater than his predecessors, he was in fact standing on the shoulders of dwarfs, a much less attractive metaphor. I intend no comparisons with Newton inwhat follows: NLP/CL has noNewtons and noNobel Prizes so far, and quite rightly. I intend only to draw attention to a tendency in our field to ignore its intellectual inheritance and debt; I intend to discharge a little of this debt in this article, partly as an encouragement to others to improve our lack of scholarship and knowledge of our own roots, often driven by the desire for novelty and to name our own systems. Roger Schank used to argue that it was crucial to name your own NLP system and then have lots of students to colonize all major CS departments, although time has not been kind to his many achievements and originalities, even though he did build just such an Empire. But to me one of the most striking losses from our corporate memory is the man who is to me the greatest of the first generation and still with us: Vic Yngve. This is the man who gave us COMIT, the first NLP programming language; the first random generation of sentences; and the first direct link from syntactic structure to parsing processes and storage (the depth hypothesis). I find students now rarely recognize his name, and find that incredible. This phenomenon is more than corporate bad memory, or being too busy with engineering to do the scholarship. It is something endemic in the wider field of Computer Science and Artificial Intelligence, although bottom-up wiki techniques are now filling many historical gaps for those who know where to look, as the generation of pioneers has time to reminisce in retirement.1 There are costs to us from this general lack of awareness, though: a difficulty of “standing on the shoulders” of others and acknowledging debts, let alone passing on software packages. Alan Bundy used to highlight this in theAISB Quarterlywith a regular columnwhere he located and pilloried reinventions in the field of AI; he also recommended giving obituaries for one’s own work, and this paper could be seen in that way, too.