Abstract
| Original language | English |
|---|---|
| Publication status | Published - 2016 |
| Event | The First International Conference on Turkic Computational Linguistics - Konya, Turkey Duration: Apr 2 2016 → Apr 8 2016 http://nur.nu.edu.kz/bitstream/handle/123456789/1692/kaz-tagger.pdf?sequence=1 |
Conference
| Conference | The First International Conference on Turkic Computational Linguistics |
|---|---|
| Abbreviated title | TurCLing 2016 |
| Country | Turkey |
| City | Konya |
| Period | 4/2/16 → 4/8/16 |
| Internet address |
Fingerprint
Cite this
A free/open-source hybrid morphological disambiguation tool for Kazakh. / Assylbekov, Zhenisbek; Washington, Jonathan; Tyers, Francis; Nurkas, Assulan; Sundetova, Aida; Karibayeva, Aidana; Abduali, Balzhan; Amirova, Dina.
2016. Paper presented at The First International Conference on Turkic Computational Linguistics, Konya, Turkey.Research output: Contribution to conference › Paper
}
TY - CONF
T1 - A free/open-source hybrid morphological disambiguation tool for Kazakh
AU - Assylbekov, Zhenisbek
AU - Washington, Jonathan
AU - Tyers, Francis
AU - Nurkas, Assulan
AU - Sundetova, Aida
AU - Karibayeva, Aidana
AU - Abduali, Balzhan
AU - Amirova, Dina
PY - 2016
Y1 - 2016
N2 - 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.
AB - 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.
M3 - Paper
ER -