Detailansicht
Characteristics of Contemporary Printed Turkish
Letter and Word Characteristics of Contemporary Printed Turkish and Author Identification
ISBN/EAN: 9783838385075
Umbreit-Nr.: 4740145
Sprache:
Englisch
Umfang: 80 S.
Format in cm: 0.5 x 22 x 15
Einband:
kartoniertes Buch
Erschienen am 14.07.2010
Auflage: 1/2010
- Zusatztext
- Models of natural languages and language characteristics are widely used in many computer science applications such as data security, language identification, spell checking, data compression, authorship attribution and speech recognition. In the scope of this study, a large scale corpus is created and used to discover language characteristics of Turkish. Word and letter based analyses are made on this corpus to build a base for several NLP studies. In the author identification part, we used two different methods based on word n- grams to identify author of an anonymous text. For 16 authors, training and test set articles are collected, and mentioned two methods are applied on these article sets. Finally, obtained results from two methods are compared with each other and most successful method is determined. This study can help professionals working on author identification, corpus linguistics, n-gram analysis, cryptanalysis, and speech recognition.
- Autorenportrait
- Feristah Örücü: She had received the B.S. and M.S. degrees in Comp Eng from DEU, Turkey. She has been a Ph.D. student and a Res Asst of Dept of Comp Eng of DEU. Gökhan Dalkiliç: He had received M.S. degrees in Comp Sci from USC, and from Ege Univ CI, Ph.D. degree in Comp Eng from DEU. He has been an Asst Prof of the Dept of Comp Eng of DEU.