FAYLDAGI OBYEKTLARNI SEMANTIK TAHLIL QILISH ALGORITMLARINI ERGONOMIK METODIKASI
Kalit so‘zlar:
sun’iy intellekt, semantik qidiruv, TF-IDF, Word2Vec, talaba javoblarini tekshirish, PDF qidiruv, matn o‘xshashligi, kosinus o‘xshashligi.Annotatsiya
Ushbu maqolada PDF formatidagi elektron adabiyotlar va fayllar ichidan kerakli ma’lumotlarni tezkor topish va ma’lumotlarini semantik jihatdan tahlil qilish masalasi ko‘rib chiqiladi. Sun’iy intellekt asosida ishlab chiqilgan semantik qidiruv algoritmi taklif etiladi. Ushbu tadqiqotda matnlarni semantik tahlil qilish uchun zamonaviy axborot qidiruv va tabiiy tilni qayta ishlash usullari qo‘llanildi. Olingan natijalar shuni ko‘rsatdiki, chuqur o‘rganish modellari klassik usullarga nisbatan yuqori aniqlikni ta’minlaydi.
Iqtiboslar
1. Abdurahmonov S. Matnlarni qayta ishlash va tabiiy til texnologiyalari. – Toshkent, 2020.
2. Axmedov J. R. Tizimli tahlil: darslik. – Jizzax: Ilm nuri print MChJ, 2023. – 266 bet.
3. Devlin J. et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // NAACL-HLT. – 2019.
4. Goldberg Y., Levy O. word2vec Explained: Deriving Mikolov et al.'s Negative-Sampling Word-Embedding Method [Electronic resource]. – 2014. – Mode of access: arXiv.
5. Jones K. S. A statistical interpretation of term specificity and its application in retrieval // Journal of Documentation. – 1972. – Vol. 28, № 1. – P. 11–21.
6. Karaboga D. et al. Automatic Short Answer Grading Using Deep Learning // Computers & Education. – 2020.
7. Karimov A., Tursunov B. Sun’iy intellekt va uning qo‘llanilishi. – Toshkent, 2021.
8. Le Q., Mikolov T. Distributed Representations of Sentences and Documents // International Conference on Machine Learning (ICML). – 2014.
9. Mikolov T. et al. Efficient Estimation of Word Representations in Vector Space [Electronic resource]. – 2013. – Mode of access: arXiv:1301.3781.
