A free/open-source hybrid morphological disambiguation tool for Kazakh

Simple item page
dc.contributor.authorAssylbekov, Zhenisbek
dc.contributor.authorWashington, Jonathan
dc.contributor.authorTyers, Francis
dc.contributor.authorNurkas, Assulan
dc.contributor.authorSundetova, Aida
dc.contributor.authorKaribayeva, Aidana
dc.contributor.authorAbduali, Balzhan
dc.contributor.authorAmirova, Dina
dc.date.accessioned2016-09-05T04:16:09Z
dc.date.available2016-09-05T04:16:09Z
dc.date.issued2016-04
dc.description.abstractThis 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.ru_RU
dc.identifier.citationAssylbekov, Zhenisbek; North, Jonathan; Tyers, Francis; Nurkas, Assulan; Sundetova, Aida; Karibayeva, Aidana; Abduali, Balzhan; Amirova, Dina. (2016). A free/open-source hybrid morphological disambiguation tool for Kazakh.; Conference Paper.ru_RU
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/1692
dc.language.isoenru_RU
dc.publisherDOI: 10.13140/RG.2.2.12467.43045ru_RU
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectopen-sourceru_RU
dc.subjectmorphological disambiguationru_RU
dc.subjecthybrid morphological disambiguation toolru_RU
dc.subjecttool for Kazakhru_RU
dc.subjectResearch Subject Categories::MATHEMATICSru_RU
dc.titleA free/open-source hybrid morphological disambiguation tool for Kazakhru_RU
dc.typeConference Paperru_RU

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
kaz-tagger.pdf
Size:
1.03 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.22 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Conference papers