SINONIMIK IBORALARNI ANIQLASHNING ASOSIY USULLARI
DOI:
https://doi.org/10.65164/fmf4sj58Ключевые слова:
GloVe algoritmi, ko‘p so‘zli ifodalar; sinonim iboralar; semantik o‘xshashlik; tabiiy tilni qayta ishlash; iboralarni vektorlash; o‘zbek tili korpusi; statik embedding modellari.Аннотация
Ko‘p so‘zli ifodalarning (iboralarning) semantik jihatdan teng bo‘lgan
variantlarini aniqlash tabiiy tilni qayta ishlashning asosiy muammolaridan biri sanaladi, ayniqsa
resurslari cheklangan tillar — jumladan o‘zbek tilida. Ushbu maqolada GloVe algoritmining o‘zbek
tilidagi sinonim iboralarni aniqlashdagi amaliy imkoniyatlari o‘rganiladi. Tadqiqot uchun 298 ta ibora
va ularning sinonimlaridan iborat maxsus to‘plam shakllantirildi. Ushbu to‘plam asosida, oldindan
o‘qitilgan 100 o‘lchamli GloVe vektorlaridan foydalanilib, iboralarning semantik ifodasi o‘rtacha
vektorlash usuli bilan hisoblandi. Iboralar orasidagi semantik yaqinlik kosinus o‘xshashligi
yordamida baholandi va sinonimlikni aniqlash uchun chegaraviy qiymat asosida tasniflash amalga
oshirildi. Olib borilgan eksperimentlar natijalari GloVe modelining o‘zbek tilidagi iboralarning
semantik o‘xshashligini aniqlashda ma’lum samaradorlikka ega ekanini ko‘rsatdi.
Библиографические ссылки
1. Rahmatullayev, Sh., Xolmanova, Z., Mahmudov, N., Orazova, I., & Rixsiyeva, K. (2022).
Phraseological Dictionary of the Uzbek Language. Tashkent: Gʻafur Gʻulom Publishing House.
Retrieved from https://gglit.uz/o-zbek-tili-frazeologik-lug-ati/ (In Uzbek)
2. Muhammedova, S., Asilova, G., & Qodirova, X. (2022). Comparative Typology of Uzbek and
Russian Languages. Retrieved from https://www.researchgate.net/publication/366837551 (In
Uzbek)
3. Rahmatullayev, Sh., Mahmudov, N., Xolmanova, Z., O‘razova, I., & Rixsiyeva, K. (2022).
Phraseological Dictionary of the Uzbek Language. Tashkent: Gʻafur Gʻulom Publishing House.
(In Uzbek)
4. Muzny, G., & Zettlemoyer, L. (n.d.). Automatic Idiom Identification in Wiktionary. Department
of Computer Science & Engineering, University of Washington, Seattle, WA. Retrieved from
5. Qiang, J., Li, Y., Zhang, C., Li, Y., Zhu, Y., Yuan, Y., & Wu, X. (n.d.). Chinese Idiom
Paraphrasing. Yangzhou University, Hefei University of Technology, Zhejiang Lab. (In
Chinese)
6. (2019). Attention-based long short-term memory network using sentiment lexicon embedding for
aspect-level sentiment analysis in Korean. Information Processing & Management. (In Korean)
7. (2020). Phrase embedding learning from internal and external information based on
autoencoder. Retrieved from
https://www.sciencedirect.com/science/article/abs/pii/S030645732030916X
8. Khodak, M., Risteski, A., Fellbaum, C., & Arora, S. (2017). Automated WordNet construction
using word embeddings. In Proceedings of the 1st Workshop on Sense, Concept and Entity
Representations and their Applications (pp. 12–23).
9. Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching word vectors with
subword information. Transactions of the Association for Computational Linguistics, 5(1), 135–
146.
10. Elov, B., Abdurakhmonova, N., Axmedova, X., Xusainova, Z., Iskandarova, A., Fattaxova, D.
(2024). Designing Processes and Models of Semantical Differentiation for Polyfunctional Words
889
in the Uzbek Contexts. In: Nguyen, N.T., et al. Recent Challenges in Intelligent Information and
Database Systems. ACIIDS 2024. Communications in Computer and Information Science, vol
2145. Springer, Singapore. https://doi.org/10.1007/978-981-97-5934-7_26
11. Boltayevich, E.B., Mirdjonovna, H.S., Ilxomovna, A.X. (2023). Methods for Creating a
Morphological Analyzer. In: Zaynidinov, H., Singh, M., Tiwary, U.S., Singh, D. (eds) Intelligent
Human Computer Interaction. IHCI 2022. Lecture Notes in Computer Science, vol 13741.
Springer, Cham. https://doi.org/10.1007/978-3-031-27199-1_4
12. E. B. Boltayevich, A. X. Ilxomovna, P. M. Hakim Qizi and K. N. Uktambay O‘g'li, "Semantic
Differentiation of Uzbek Homonyms Using the Lesk Algorithm," 2023 8th International
Conference on Computer Science and Engineering (UBMK), Burdur, Turkiye, 2023, pp. 137-
140, doi: 10.1109/UBMK59864.2023.10286666.
