6-825msg2.txt

运用贝叶斯网编的一个识别垃圾邮件的程序

Subject: re : 6 . 797 , comparative method : n - ary comparison

critic of manaster ramer miss the main point : janhunen call by " similarity " parallel between japanese and other altaic language based on regular phonetic correspondences without bother to prove that these be real " look - alike " . the parallel base on regular correspondence be not chance or random parallel and therefore the propose statistical game do not apply to the case . if you do not believe it , take any pair of a priorus unrelate language , such as for example mandarin and eskimo , and try to establish regulum r phonetic correspondence . needless to say , add to this company zulu , basque , and nivx be not go to " improve " the picture . alexander vovin avvovin @ miamiu . ac . muohio . edu