Çoklu Koşullu Rassal Alanlar Kullanarak Türkçe Biçimbilimsel Belirsizlik Giderme

Abstract

Bu çalışma Türkçenin biçimbilimsel belirsizlik gidermesi sorunu ile uğraşır. Bu sorunu istatistiksel makine öğrenme yöntemi ile ele alar. Kullandığı istatistiksel yöntem ise koşullu rassal alanlardır.

This thesis presents the results of main part-of-speech tagging and full morphological disambiguation of Turkish sentences using multiple Conditional Random Fields (CRFs). Although CRFs are applied to many different languages for part-of-speech (POS) tagging, Turkish poses interesting challenges to be modeled with them. The challenges include issues related to the statistical model of the problem as well as issues related to computational complexity and scaling. In this paper, we propose a novel model for main-POS tagging in Turkish. Furthermore, we pro- pose some approaches to reduce the computational complexity and allow better scaling characteristics or improve the performance without increased complexity. These approaches are discussed with respect to their advantages and disadvantages. We show that the best approach is competitive with the current state of the art in accuracy and also in training and test durations. The good results obtained imply a good first step towards full morphological disambiguation.