|
Title:
|
CYBERSQUATTING DETECTION BY AUTOMATIC DOMAIN NAME RE-ACCENTING |
|
Author(s):
|
Jean Ceccato, Anthony Don |
|
ISBN:
|
978-989-8533-09-8 |
|
Editors:
|
Bebo White and Pedro Isaías |
|
Year:
|
2012 |
|
Edition:
|
Single |
|
Keywords:
|
Domain name re-accenting, Cybersquatting, Internationalized Domain names, Natural language processing |
|
Type:
|
Full Paper |
|
First Page:
|
195 |
|
Last Page:
|
202 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In 2012 it has become possible to buy accented .fr and .it domain names (AFNIC, 2012) (Euro DNS, 2012). Numerous people have raised concerns about this decision(Honorat, 2012) (Un simple clic, 2012). They are expecting a huge rise of cybersquatting. The current paper presents a method to automatically find relevant accented forms of an unaccented domain name in order to help protecting ones trademark against cybersquatters. Although re-accenting texts has been a widely-tackled issue, it has always been done with the hypothesis that the language used was known or that the context would be sufficient to determine it. Domain names do not have blank or coma separators, they have a very short context and an almost nonexistent syntax. The proposed method generates the most relevant accented forms for the considered languages. This method actually works with six different languages (French, Spanish, Italian, German Polish and Portuguese) and the implementation has been designed keeping in mind the ability to add new languages, provided that the needed documents to initialize the model are supplied (a dictionary and a large corpus of texts). |
|
|
|
|
|
|
