词汇密度计算发展趋势分析

Trends in Computation of Lexical Density

词汇密度是作者身份鉴定研究的一个语言特征值,其重要性很早就被认识。从简单的词形词类比到繁杂的计算公式,再到相应的计算软件,词汇密度计算不断地得到发掘。目前其已经发展到一个新的阶段,即与别的语言特征结合在一起,为文体自动辨识和作者身份鉴定研究提供更为准确和全面的参考依据。这也反映出建立一个完整的作者身份鉴定软件系统的必要性。

Lexical richness is a value of language feature in authorship attribution,the function of which has been acknowledged early in the academics. From the simple type / token ratio to complex computation formula till the related software program,approaches to computing lexical richness have been used one after another. Up to now,other language features have to be determined in order to offer a more accurate and comprehensive reference to automatic stylistic recognition and authorship attribution. Therefore,it is necessary to develop more effective softwares for authorship attribution.