Research Area:  Machine Learning
The word2vec model and application by Mikolov et al. have attracted a great amount of attention in recent two years. The vector representations of words learned by word2vec models have been shown to carry semantic meanings and are useful in various NLP tasks. As an increasing number of researchers would like to experiment with word2vec or similar techniques, I notice that there lacks a material that comprehensively explains the parameter learning process of word embedding models in details, thus preventing researchers that are non-experts in neural networks from understanding the working mechanism of such models. This note provides detailed derivations and explanations of the parameter update equations of the word2vec models, including the original continuous bag-of-word (CBOW) and skip-gram (SG) models, as well as advanced optimization techniques, including hierarchical softmax and negative sampling. Intuitive interpretations of the gradient equations are also provided alongside mathematical derivations.
Keywords:  
Author(s) Name:  Xin Rong
Journal name:  arXiv.org/cs
Conferrence name:  
Publisher name:  arXiv.org
DOI:  arXiv:1411.2738
Volume Information:  arXiv:1411.2738
Paper Link:   https://arxiv.org/abs/1411.2738