SEMINAR

 DEPARTMENT OF COMPUTER ENGINEERING

ABSTRACT

Statistical Language Modeling for Turkish

 

Dilek Zeynep Hakkani

Ph.D. in Computer Engineering

Supervisor: Assoc. Prof. Dr. Kemal Oflazer

October 8, 1999

 

Recent advances in computer hardware and availability of very large corpora have made the application of statistical techniques to natural language processing a possible, and a very appealing research area. Many good results have been obtained by applying these techniques to English (and similar languages) in parsing, word sense disambiguation, part-of-speech tagging, and speech recognition. However, languages like Turkish, which have a number of characteristics that differ from English (such as agglutinative or inflective morphology and relatively free constituent order), have mainly been left unstudied.

 

In this Ph.D. thesis, I propose to study the development and application of statistical language modeling techniques for Turkish, and test such techniques on basic applications of natural language processing like morphological disambiguation and noun phrase (NP) extraction.

 

 

The Seminar will be on October 8, 1999, at 15:00

in EA331