A customizable, self-learning parameterized MT system: the next generation

MT Summit VII Sept. 1999 Chart Translation Martin Kay Stanford University and Xerox Palo Alto Research Center Abstract For efficiency reasons, Machine Translation systems are generally designed to eliminate ambiguities as early as possible even if delay- ing the decision would make a more informed choice possible. This paper takes the contrary view, arguing that essentially all choices should be deferred so that large num- bers of competing translations will be pro- duced in typical cases. Representing all the data structures in a suitable packed form, much as alternative structures are represented in a chart parser, makes this practicable. 1 Translation and Knowledge Judging by the great increase in activity in machine transla- tion in the last few years, an outside observer might easily conclude that researchers in the field had finally reached the goal of truly practical translation systems towards which they have been striving for some forty years. Maybe some breakthrough has occurred, or maybe all the little incremen- tal efforts has finally proved just enough to push us over an important invisible line. Insiders know differently. If we somehow seem to be winning the game that has been going against us for so long, it is not because we have learnt to play better; it is because the goal posts have been moved. Simply stated, the market for low-quality machine transla- tion has grown from nothing to one clearly worthy of com- mercial interest in a matter of two or three years. Whatever the reasons may be for this change in the translation market, the Worldwide Web surely played an important part. Browsers now routinely offer happy explor- ers the opportunity to have the results of their quests trans- lated into their own language at the click of a mouse. Their expectations of this process are, however, no greater than they were of the initial search. Web usage is essentially casual, even when a lot could turn on the outcome. If our search comes up with nothing, at least little time will have been lost. If we find something useful, it will be frosting on the cake—something we knew we had no real right to expect. So it is with a translation that is offered. If by read- ing it fast with little attention to detail, we seem to perceive something in it that touches on the subject of our quest, at best we may gain some useful information; at worst we will be amused. There will continue to be a market for this kind of translation until substantially better results can be produced with little or no increase in the price. But there is also a great and growing need for high-quality translation and, as I have argued repeatedly (Kay et al. 1994, Kay 1997), com- puters will do little to help fill this need until very large strides have been made towards building programs that could pass the Turing test—programs that could, in other words, successfully masquerade as human beings on the other end of …

Content truncated to 500 words