O'ZBEK TILI IBORALARINI ANIQLASHDA LSA VA LDA GIBRID MODELI
Article Sidebar
Main Article Content
Abstract
Iborani gapda avtomatik topish mashinaviy tarjimaning dastlabki va hal qiluvchi bosqichidir. Ushbu ishda matn to‘plamidan avtomatik o‘rganiladigan ikki mavzu modeli, yashirin semantik tahlil (LSA) va yashirin Dirixle taqsimoti (LDA), bitta gibrid belgilar to‘plamiga birlashtirilib, shu to‘plamning o‘zbek iboralari ontologiyasidan olingan belgilarga qo‘shimcha bera olishi tekshirildi. Sinov 860 ta belgilangan gap, 1,07 million leksemali matn to‘plami va 2 098 iborali ontologiya asosida uch xil tasniflagichda o‘tkazildi. Gibrid mavzu belgilari o‘zi alohida olinganda F1 0,52 dan 0,57 gacha darajada qoldi, ontologiya belgilari ustiga qo‘shilganda esa uchala tasniflagichda ham natijani kamaytirdi va bu kamayish McNemar mezoni bo‘yicha ishonchli. Shu asosda hujjat darajasidagi mavzu modellari ibora aniqlash uchun yaroqsiz, ontologiya esa hal qiluvchi manba degan xulosa chiqariladi.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
O‘zbekiston Respublikasi Prezidentining 2024 yil 14 oktabrdagi PQ 358 sonli Sun’iy intellekt texnologiyalarini 2030 yilga qadar rivojlantirish strategiyasini tasdiqlash to‘g‘risidagi qarori. lex.uz.
Baldwin T., Kim S.N. Multiword expressions. Handbook of Natural Language Processing, 2nd ed. Boca Raton, CRC Press, 2010, pp. 267–292.
Nazirova E., Abdurakhmonova N., Madetbayeva N. O‘zbek tili iboralari ontologiyasi va o‘xshashlik o‘lchovlari. UBMK 2026.
Deerwester S., Dumais S.T., Furnas G.W., Landauer T.K., Harshman R. Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6), 1990, pp. 391–407.
Blei D.M., Ng A.Y., Jordan M.I. Latent Dirichlet allocation. Journal of Machine Learning Research, 3, 2003, pp. 993–1022.
Griffiths T.L., Steyvers M. Finding scientific topics. Proceedings of the National Academy of Sciences, 101 (suppl. 1), 2004, pp. 5228–5235.
Mimno D., Wallach H., Talley E., Leenders M., McCallum A. Optimizing semantic coherence in topic models. Proceedings of EMNLP 2011, Edinburgh, 2011, pp. 262–272.