Tixierae/deep_learning_NLP
A collection of deep learning implementations for NLP tasks including neural machine translation, word embeddings, and attention mechanisms.
Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
This repository provides Keras, PyTorch, and NumPy implementations of classical deep learning architectures for natural language processing. It includes a fully functional seq2seq neural machine translation model with multiple attention mechanisms (dot, general, concat), implementations of Word2vec and Doc2vec trained from scratch using only NumPy, hierarchical attention networks, and various sequence modeling techniques. All implementations are well-commented and designed for educational purposes.