O‘ZBEK TILIDAGI OMONIM LEKSEMALARNI KONTEKST ASOSIDA AVTOMATIK FARQLASHNING LINGVISTIK VA METODOLOGIK ASOSLARI
DOI:
https://doi.org/10.67227/ancmmk61Kalit so‘zlar:
omonimiya, omonim leksema, WSD, kontekstual tahlil, semantik differensiallash, UzBERT, XLM-R, F1.Abstrak
Maqolada o‘zbek tilidagi omonim leksemalarni kontekst asosida avtomatik farqlash muammosi lingvistik va metodologik jihatdan tahlil qilingan. Tadqiqot o‘zbek tilidagi ayrim omonim leksemalar misolida lotin va kirill yozuvlarida ikkita kontekstual model — UzBERT va XLM-R yordamida olib borilgan. Har bir leksemaning turli ma’nolariga oid kontekstlar kosinus o‘xshashligi asosida taqqoslanib, ichki va tashqi o‘xshashlik ko‘rsatkichlari hamda ular orasidagi ajratish farqi hisoblangan. Natijalar xalqaro miqyosda tan olingan F1 baholash ko‘rsatkichi orqali qo‘shimcha ravishda tasdiqlangan: UzBERT oltita sinov holatining beshtasida 80% dan yuqori F1 ko‘rsatkichiga erishgan, XLM-R esa 20% dan 100% gacha keskin beqarorlikni namoyon etgan. Ushbu natijalar tilga xos oldindan o‘qitilgan modellarning ko‘p tilli modellarga nisbatan o‘zbek tilidagi omonimiyani farqlashda barqarorroq ishlashini ko‘rsatadi.
Yuklashlar
Havolalar
1. Abduraxmonova N. Mashina tarjimasi tizimlari uchun lingvistik ta’minot masalalari. – Toshkent: Fan, 2018. – 184 b.
2. Abduraxmonova N. O‘zbek tili tezaurusini yaratishda standart me’yorlar // Til va adabiyot ta’limi. – Toshkent, 2024. – № 3. – B. 45–49.
3. Abduraxmonova N., Adalı E., Shamieva N. Semantic Relationships Between Synset Adjectives for English-Uzbek Bilingual Thesaurus // 2025 10th International Conference on Computer Science and Engineering (UBMK). – 2025. – P. 305–310. – DOI: 10.1109/UBMK67458.2025.11206834. Maqola va mualliflar tarkibi tasdiqlandi. ResearchGate
URL: DOI orqali maqola
4. Abduraxmonova N., Rajabova K. Stages of Creating Uzbek Language Multimedia Corpus // 2025 10th International Conference on Computer Science and Engineering (UBMK). – 2025. – P. 1628–1633. – DOI: 10.1109/UBMK67458.2025.11206927. Sahifalar va konferensiya ma’lumotlari tasdiqlandi. DOI
URL: IEEE/DOI sahifasi
5. Abduraxmonova N., Shamsiyeva G. Context-Based Multilingual Translation Technology: On the Example of the Paratranslator Platform // 2025 10th International Conference on Computer Science and Engineering (UBMK). – 2025. – P. 1756–1760. – DOI: 10.1109/UBMK67458.2025.11206971. ResearchGate URL: DOI orqali maqola
6. Agostini A., Usmanov T., Khamdamov U., Abdurakhmonova N., Mamasaidov M. UZWORDNET: A Lexical-Semantic Database for the Uzbek Language // Proceedings of the 11th Global Wordnet Conference. – 2021. – P. 8–19. – DOI: 10.18653/v1/2021.gwc-1.2. ACL Anthology URL: ACL Anthology
7. Basile P., Siciliani L., Musacchio E., Semeraro G. Exploring the Word Sense Disambiguation Capabilities of Large Language Models // arXiv preprint arXiv:2503.08662. – 2025. Maqola 2025-yil 11-martda taqdim etilgan. arXiv
URL: arXiv
8. Conneau A., Khandelwal K., Goyal N., Chaudhary V., Wenzek G., Guzmán F., Grave E., Ott M., Zettlemoyer L., Stoyanov V. Unsupervised Cross-Lingual Representation Learning at Scale // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. – 2020. – P. 8440–8451. – DOI: 10.18653/v1/2020.acl-main.747. ACL Anthology URL: ACL Anthology
9. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proceedings of NAACL-HLT 2019. – Minneapolis, Minnesota, 2019. – P. 4171–4186. – DOI: 10.18653/v1/N19-1423. ACL Anthology URL: ACL Anthology
10. Du J., Qi F., Sun M. Using BERT for Word Sense Disambiguation // arXiv preprint arXiv:1909.08358. – 2019. arXiv
URL: arXiv
11. Ercan G., Yıldız O. T. AnlamVer: Semantic Model Evaluation Dataset for Turkish – Word Similarity and Relatedness // Proceedings of the 27th International Conference on Computational Linguistics. – Santa Fe, New Mexico, USA, 2018. – P. 3819–3836. ACL Anthology URL: ACL Anthology
12. Hadiwinoto C., Ng H. T., Gan W. C. Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations // Proceedings of EMNLP-IJCNLP 2019. – Hong Kong, China, 2019. – P. 5297–5306. – DOI: 10.18653/v1/D19-1533. ACL Anthology URL: ACL Anthology
13. İlgen B. Türkçe sözcük anlam belirsizliği giderme: Doktora tezi. – İstanbul: İstanbul Teknik Üniversitesi, 2015. – 165 s.
14. Kohavi R. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection // Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence (IJCAI 1995). – 1995. – Vol. 2. – P. 1137–1145. ML Anthology URL: IJCAI rasmiy PDF
15. Loureiro D., Rezaee K., Pilehvar M. T., Camacho-Collados J. Analysis and Evaluation of Language Models for Word Sense Disambiguation // Computational Linguistics. – 2021. – Vol. 47, No. 2. – P. 387–443. – DOI: 10.1162/coli_a_00405. DOI URL: MIT Press / DOI
16. Manning C. D., Raghavan P., Schütze H. Introduction to Information Retrieval. – Cambridge: Cambridge University Press, 2008. – 482 p. Stanford NLP URL: Stanford kitob sayti
17. Mansurov B., Mansurov A. UzBERT: Pretraining a BERT Model for Uzbek // arXiv preprint arXiv:2108.09814. – 2021. arXiv
URL: arXiv
18. Navigli R. Word Sense Disambiguation: A Survey // ACM Computing Surveys. – 2009. – Vol. 41, No. 2. – Article 10. – P. 1–69. – DOI: 10.1145/1459352.1459355. ResearchGate URL: DOI / ACM
19. Proietti L., Perrella S., Tedeschi S., Vulpis G., Lavalle L., Sanchietti A., Ferrari A., Navigli R. Analyzing Homonymy Disambiguation Capabilities of Pretrained Language Models // Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). – Torino, Italy, 2024. – P. 924–938. ACL Anthology URL: ACL Anthology
20. Raganato A., Camacho-Collados J., Navigli R. Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison // Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. – Valencia, Spain, 2017. – P. 99–110. ACL Anthology
URL: ACL Anthology
21. Reif E., Yuan A., Wattenberg M., Viégas F. B., Coenen A., Pearce A., Kim B. Visualizing and Measuring the Geometry of BERT // Advances in Neural Information Processing Systems. – 2019. – Vol. 32. – P. 8592–8600. proceedings.neurips.cc
URL: NeurIPS rasmiy sahifasi
22. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser Ł., Polosukhin I. Attention Is All You Need // Advances in Neural Information Processing Systems. – 2017. – Vol. 30. – P. 5998–6008. proceedings.neurips.cc
URL: NeurIPS rasmiy sahifasi
23. Zhou X., Huang H., Chi Z., Ren M., Gao Y. RS-BERT: Pre-training Radical Enhanced Sense Embedding for Chinese Word Sense Disambiguation // Information Processing & Management. – 2024. – Vol. 61, No. 4. – Article 103740. – DOI: 10.1016/j.ipm.2024.103740.
Muhim tuzatish: sizdagi 103712 noto‘g‘ri; Elsevier rasmiy yozuvida maqola raqami 103740. ScienceDirect
URL: ScienceDirect / DOI
24. Каушинис Т. В., Кириллов А. Н., Коржицкий Н. И., Крижановский А. А., Пилинович А. В. и др. Обзор методов и алгоритмов разрешения лексической многозначности: введение // Труды Карельского научного центра РАН. – Петрозаводск, 2015. – № 8. – С. 3–23.
25. Хомицевич О. Г., Рыбин С. В., Аничкин И. М. Использование лингвистического анализа для нормализации текста и снятия омонимии в системе синтеза русской речи // Известия высших учебных заведений. Приборостроение. – 2013. – Т. 56, № 2. – С. 45–50. Открытые книги URL: ITMO OpenBooks maqola sahifasi
