Lexicon-free stemming for Kazakh language information retrieval

Ualsher Tukeyev, Aliya Turganbayeva, Balzhan Abduali, Diana Rakhimova, Dina Amirova, Aidana Karibayeva

2018

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaict.2018.8747021
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

In paper are considered existing algorithms for automatically isolating the bases for a number of natural languages and possible ways of synthesizing a normal form of a word for the Kazakh language. In paper are described the complete system of endings of the Kazakh language. The paper proposes a new approach to constructing a lexicon-free stemming algorithm for the Kazakh language on the basis of a complete set of endings of the Kazakh language. The stemming algorithm will be used for Kazakh language information retrieval to finding specific words in the documents by stemming base of word.