From: Improved content recommendation algorithm integrating semantic information
Training Corpus | Chinese Wikipedia |
---|---|
Corpus size | 1.3G |
Vector dimension | 300 |
Word segmentation tool | jieba |
Training tools | Word2Vec of Gensim |
Training model | Skip-Gram with Negative Sampling |
Training parameters | The dynamic window size is 5. The minimum word frequency is 10. The number of iterations is 5 |