DocumentCode :
1197085
Title :
A hybrid model for the prediction of the linguistic origin of surnames
Author :
Bonaventura, Patrizia ; Gori, Marco ; Maggini, Marco ; Scarselli, Franco ; Sheng, Jianqing
Author_Institution :
Conversation Comput. Corp., Redmond, WA, USA
Volume :
15
Issue :
3
fYear :
2003
Firstpage :
760
Lastpage :
763
Abstract :
The prediction of the linguistic origin of surnames is a basic functionality required in the design of high-quality multilanguage speech synthesizers. The assignment of a given string representing a surname to a specific language is typically based on a set of rules which can hardly be written in an explicit form. The approach we propose faces this problem combining a rule-based system with a module based on evidential reasoning and a module based on neural networks. The resulting hybrid system combines the different sources of information, merging both knowledge from experts on linguistics and knowledge automatically acquired using learning from examples. The system has been validated on a large database containing surnames belonging to four different languages, showing its effectiveness for real-world applications.
Keywords :
case-based reasoning; knowledge based systems; learning by example; linguistics; natural languages; neural nets; speech synthesis; very large databases; evidential reasoning; hybrid model; knowledge acquisition; large database; learning from examples; merging; multilanguage speech synthesizers; neural networks; rule-based system; rules; speech synthesis; string; surname linguistic origin prediction; Computer architecture; Databases; Information resources; Knowledge based systems; Merging; Neural networks; Predictive models; Speech synthesis; Synthesizers; Telephony;
fLanguage :
English
Journal_Title :
Knowledge and Data Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
1041-4347
Type :
jour
DOI :
10.1109/TKDE.2003.1198404
Filename :
1198404
Link To Document :
بازگشت