摘要：Draw a stock of n-letter words in decreasing order of frequency from Kucera and Francis's Computational Analysis of Present-Day American English until they yield a double word square. For n=2,3,4,5, word stocks of 15,66,326 and 1444 are needed, in good agreement with Chris Cole's theoretical predictions of 16, 63, 250 and 992 given in "Mathematics of Square Construction" in February 1993. The Kucera and Francis frequencies (in word per million) are given next to the words in each square.
