Perform embedding of words in the text so that it has the highest relationship with the embedding of the document label.
Create skip gram dataset for training
python data/generated_data/generate_data.py
Train skip gram model
python train_word2vec.py
Train classifier
python classifier.py
Train | Test | Validation |
---|---|---|
1.0 |
0.973 |
0.979 |
Pythonic Excursions: Optimize Computational Efficiency of Skip-Gram with Negative Sampling