MASHINALI O’RGATISH USULLARI YORDAMIDA MATNLI HUJJATLARNI MAZMUNIGA KO’RA TASNIFLASH
Ключевые слова:
Matnlarni tasniflash, mashinali o‘rgatish, O‘rama neyron tarmoqlari (CNN), CNN texnikalari, konvolyutsiya, pooling, embedding, yangiliklar maqolalari, avtomatik tasniflash, algoritmlar taqqoslanishi, aniqlik, samaradorlik.Аннотация
Mazkur tadqiqot ishida matnli hujjatlarni mazmuniga ko‘ra avtomatik tasniflash uchun mashinali o‘rgatish usullaridan biri – O‘rama neyron tarmoqlari (CNN) tahlil qilindi. Tadqiqot jarayonida yangiliklar saytlaridan olingan turli mavzularga oid matnli maqolalardan tashkil topgan datasetdan foydalanildi. CNN algoritmi yordamida ushbu ma'lumotlar ustida amaliy tajribalar o‘tkazildi.
Olingan natijalar asosida CNN usulining samaradorligi klassik mashinali o‘rgatish algoritmlari bilan taqqoslanib, mazkur yondashuvning matnlarni avtomatik tasniflash vazifasida yuqori aniqlik va samaradorlik kabi afzalliklari mavjudligi ko‘rsatib
berildi. Natijalar CNN modelining matnli hujjatlarni tasniflash sohasidagi istiqbolli ekanligini isbotladi.
Библиографические ссылки
1. N Ignatev, D Saidov, U Tuliev. Cluster analysis of document collections based on
topological properties of objects// AIP Conference Proceedings, 2024, Volume 3244,
Issue 1.https://doi.org/10.1063/5.0242564.
2. D Saidov, S Eshbadalov. Analysis of classification of text documents according to
the content using machine learning methods: Analysis of classification of text
documents according to the content... MODERN PROBLEMS AND PROSPECTS
OF APPLIED MATHEMATICS, 2024/6/7, Volume 1, Issue 01.
3. Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification.
Proceedings of the 2014 Conference on Empirical Methods in Natural Language
Processing (EMNLP), 1746–1751. https://doi.org/10.3115/v1/D14-1181
.
4.
Zhang, X., Zhao, J., & LeCun, Y. (2015). Character-level Convolutional
Networks for Text Classification. In Advances in Neural Information Processing
Systems (NeurIPS), 28, 649–657.
5. Matnli hujjatlarni Mashinali oʻrgatish usullari yordamida tasniflash. Saidov
Doniyor, Yusupov Jaloliddin. Vol.1No12(2024). Dece
