Stemming algorithm for Kazakh Language using rule-based approach

Nazerke Sultanova, Kanat Kozhakhmet, Ruslan Jantayev, Azhar Botbayeva

2019

Closed access Metadata (CSL-JSON)
DOI 10.1109/icecco48375.2019.9043253
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This paper considers construction of Kazakh language words. Kazakh language is the type of Turkic languages or alternatively called - agglutinative language where words are formed by attaching the finite sequence of suffixes. Kazakh morphology investigation was the main work done in construction of rule-based stemming algorithm. Stemmer algorithm will be useful in development of sentiment analysis for Kazakh language, because of its rareness and competency. Stemming algorithm works with aim to cut ending combinations. The results checked by using Machine Learning algorithms using annotated dataset, which were retrieved from KazCorpus dataset [7].