Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
The excellence of a translation should be measured by the extent to which it preserves the exact meaning of the original. But so long as we have no accepted definition of meaning, much less of exact meaning, it is difficult to use such a measure. As a practical alternative, therefore, we must search for more modest, yet better defined, procedures. | Mechanical Translation vol.3 no.3 December 1956 pp. 73-80 Some Psychological Methods for Evaluating the Quality of Translations f George A. Miller and J. G. Beebe-Center Harvard University Cambridge Massachusetts The excellence of a translation should be measured by the extent to which it preserves the exact meaning of the original. But so long as we have no accepted definition of meaning much less of exact meaning it is difficult to use such a measure. As a practical alternative therefore we must search for more modest yet better defined procedures. The present article attempts to survey some of the possible methods One can ask the opinion of several competent judges. Or given a translation of granted excellence one can compare test translations with this criterion by a variety of statistical indices. Or a person who has read only the translation may be required to answer questions based on the original. The characteristic advantages and disadvantages of each method are illustrated by examples. ONE HEARS it said that MT is currently rather crude but that workers in the field are striving to improve and refine their translations. A brief encounter with the unedited output of an automatic dictionary is sufficient evidence of the tremendous range of quality between the simplest mechanical translation and the product of a skilled human translator. The question is whether this intuitive judgment of the quality of a translation can be made more precise by any psychological techniques of scale construction. A scale of the quality of translations should be reliable valid objective and easy to use. In addition to these general desiderata for all scaling procedures there are certain special features that this particular scale should have. For example it should be applicable to any translation whether produced by a machine or by a human translator. This feature would enable us to compare the output of a particular machine to the output of a human who had had a known number
