O‘ZBEK TILI UCHUN UNIVERSAL BOG‘LIQLIK DARAXTI KORPUSI ASOSIDA CHUQUR BI-AFFIN TOBELIK TAHLILINING NEYRON MODELI
daraxtsimon korpusi va uning asosida qurilgan chuqur bi-affin neyron tobelik tahlil modeli
taqdim etiladi. Korpus o‘zbek adabiy va ilmiy-ommabop matnlaridan tanlangan 686 ta gapni
(taxminan 7 800 ta token) o‘z ichiga oladi va INCEpCTION platformasida tilshunoslar hamda
NLP muhandislari tomonidan yuqori annotatorlararo moslik (lemmatizatsiya va UPOS bo‘yicha
> 95%) bilan belgilandi. Sintaktik tahlil uchun [3] tomonidan taklif etilgan chuqur bi-affin neyron
diqqat mexanizmi arxitekturasiga asoslangan model qurilib, BiLSTM enkoder va bosh-tobe so‘z
juftliklari uchun bi-affin baholash funksiyasi yordamida tobelik grafigi optimallashtirildi. Stanza
kutubxonasiga integratsiyalashgan neyron quvur (tokenizatsiya, POS-tagging, morfologik tahlil
va dependency parsing) bo‘yicha olib borilgan tajribalar morfologiya kuchli bo’lgan sharoitida
Unlabeled Attachment Score (UAS) 69:21% va Labeled Attachment Score (LAS) 53:21% natijalarini
ko‘rsatdi; bu ko‘rsatkichlar o‘zbek tili uchun chuqur neyron tobelik tahlilining birinchi mustahkam
bazaviy modeli sifatida taklif etiladi va keyingi matematik hamda amaliy tabiiy tillar jarayoni
tadqiqotlari uchun poydevor bo‘lib xizmat qiladi.
1. John Carroll. 2010. Book Review: Dependency Parsing by Sandra Kubler, Ryan McDonald, and Joakim
Nivre. Computational Linguistics, 36(1).
2. Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Jan Hajic, Christopher D. Manning, Sampo
Pyysalo, Sebastian Schuster, Francis Tyers, and Daniel Zeman. 2020. Universal Dependencies v2: An
Evergrowing Multilingual Treebank Collection. In Proceedings of the Twelfth Language Resources and
Evaluation Conference, pages 4034-4043, Marseille, France. European Language Resources Association.
3. Dozat, T., & Manning, C. D. (2017). Deep Biaffine Attention for Neural Dependency Parsing. ICLR 2017.
4. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python
Natural Language Processing Toolkit for Many Human Languages. In Proceedings of the 58th Annual
Meeting of the Association for Computational Linguistics: System Demonstrations, pages 101-108, Online.
Association for Computational Linguistics.
5. Matlatipov, S. G., et al. (2024). UzUDT: Universal Dependencies Treebank for Uzbek. National University
of Uzbekistan.
6. McEnery T, Hardie A. Corpus Linguistics: Method, Theory and Practice. Cambridge University Press;
2011
Copyright (c) 2025 «ВЕСТНИК НУУз»
Это произведение доступно по лицензии Creative Commons «Attribution-NonCommercial-ShareAlike» («Атрибуция — Некоммерческое использование — На тех же условиях») 4.0 Всемирная.
.jpg)
2.png)
