Feature instability as a criterion for selecting potential style markers

被引：33

作者：

Koppel, Moshe ^{[1
]}

Akiva, Navot ^{[1
]}

Dagan, Ido ^{[1
]}

机构：

[1] Bar Ilan Univ, Dept Comp Sci, IL-52900 Ramat Gan, Israel

来源：

JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY | 2006年 / 57卷 / 11期

关键词：

D O I：

10.1002/asi.20428

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We introduce a new measure on linguistic features, called stability, which captures the extent to which a language element such as a word or a syntactic construct is replaceable by semantically equivalent elements. This measure may be perceived as quantifying the degree of available "synonymy" for a language item. We show that frequent, but unstable, features are especially useful as discriminators of an author's writing style.

引用

页码：1519 / 1525

页数：7

共 14 条

[1] Barzilay R, 2001, 39TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P50
[2] Caropreso MF, 2001, TEXT DATABASES AND DOCUMENT MANAGEMENT: THEORY AND PRACTICE, P78
[3] DAGAN I, 1997, P 2 C EMP METH NAT L, P55
[4] AUTHORSHIP ATTRIBUTION
HOLMES, DI
[J]. COMPUTERS AND THE HUMANITIES, 1994, 28 (02): : 87 - 106
[5] Koppel M., 2002, Literary & Linguistic Computing, V17, P401, DOI 10.1093/llc/17.4.401
[6] Lewis D., 1997, Reuters-21578 text categorization test collection, distribution 1.0
[7] Lewis D.D., 1994, 3 ANN S DOC AN INF R, V33, P81
[8] Littlestone N., 1988, Machine Learning, V2, P285, DOI 10.1007/BF00116827
[9] MLADENIC D, 1998, P 10 EUR C MACH LEAR, P95
[10] Mosteller F., 2012, APPL BAYESIAN CLASSI

← 1 2 →