5-1286msg1.txt

运用贝叶斯网编的一个识别垃圾邮件的程序

Subject: re : 5 . 1254 typological classification

for what it be worth , i disagree with martin haspelmath ( and agree with fritz newmeyer ) about the problem of define the concept with which typological work operate . but we need to make sure that this do not become a political thing : i do n't see any difference on this point between the work of typologist / functionalist as compare to that of formalist . everybody who try to compare two or more language have these problem . for ex . , in reference to the basic word order question , i notice a long time ago that some language which be claim to have ovs as basic actually rarely have both o and s at the same time in the same sentence , so i argue that maybe the term " basic " should not be apply there in the way in which it apply to english svo pattern . there be many many example where we compare incomparable and do not compare comparable because our concept be vague and our terminology be ambiguous . i have , for example , publish some papers document the confusion surround the term ' topic ' in the typological literature . there seem to be a lot of confusion likewise about the concept of ' ergative ' and ' passive ' . and it seem to me that typological category such as ' configurational ' ( or non ) , ' pro-drop ' ( or non ) , and so on , be just as poorly define and just as liable to lead to all kind of confusion .