Zipf's Law for Indian Languages

被引:22
作者
Jayaram, B. D. [1 ]
Vidya, M. N. [1 ]
机构
[1] Cent Inst Indian Languages, Mysore 570006, Karnataka, India
关键词
D O I
10.1080/09296170802326640
中图分类号
H0 [语言学];
学科分类号
030303 ; 0501 ; 050102 ;
摘要
The present paper attempts to study the application of Zipf's law for Indian languages. It examines the rank-frequency distribution in four Indian languages representing two Indo-Aryan and two Dravidian languages. The sample texts were drawn from five different genres viz., aesthetics, commerce, natural physical and professional sciences, official and media languages, and social sciences. The rank-frequency distributions were analysed for fitting the distribution by using Altmann Fitter software where it fitted the truncated zeta distribution defined as P(x) = 1/x(a)T, x = 1,2, ..., R where R is the truncation parameter and T is the normalizing constant. The analysis shows that rank-frequency distribution follows Zipf's law.
引用
收藏
页码:293 / 317
页数:25
相关论文
共 15 条
[1]  
[Anonymous], BIBLIO QUANTITATIVE
[2]  
[Anonymous], 1949, Human behaviour and the principle of least-effort
[3]  
BAAYEN RH, 2001, WORD FREQUENCY STUDI
[4]  
Barker MAAR., 1969, An Urdu Newspaper Word Count
[5]  
DABBS JA, 1966, WORD FREQUENCIES NEW
[6]  
Estoup J.B., 1916, Gammes Stenographiques
[7]  
Ghatage AM., 1964, Phonemic and Morphemic Frequencies in Hindi
[8]  
GHATAGE AM, 1994, PHONEMIC MORPHEMIC F
[9]  
JAYARAM BD, 2001, LANG ENG S AS LANG N
[10]  
JAYARAM BD, 2005, PROBLEMS QUANTITATIV, P323