armenian-news-clustering

1Shadowscale1/armenian-news-clustering

Пакет для кластеризации новостных статей на армянском языке с использованием современных методов NLP и машинного обучения

Python Stars: 0 Forks: 0 Language/NLP

Summary

A Python package for clustering and deduplicating Armenian news articles using NLP and machine learning techniques. It includes modules for data loading, text preprocessing, embedding generation with pre-trained models, named entity recognition, triplet generation for model fine-tuning, similarity calculation, clustering, and visualization.

Similar Projects