This paper presents the results of developing a morphological disambiguation tool for Kazakh. Starting with a previously developed rule-based approach, we tried to cope with the complex morphology of Kazakh by breaking up lexical forms across their derivational boundaries into inflectional groups and modeling their behavior with statistical methods. A hybrid rule-based/statistical approach appears to benefit morphological disambiguation demonstrating a per-token accuracy of 91% in running text.
|Publication status||Published - 2016|
|Event||The First International Conference on Turkic Computational Linguistics - Konya, Turkey|
Duration: Apr 2 2016 → Apr 8 2016
|Conference||The First International Conference on Turkic Computational Linguistics|
|Abbreviated title||TurCLing 2016|
|Period||4/2/16 → 4/8/16|