调试Spark MLlib自带的官方特征提取示例时,对于Word2Vec输出的结果不是很明白,参考其他资料后了解了输出结果的含义,记录一下:
Word2Vec输出的结果如下:
结果向量说明:
Word2Vec is a ML method of building a language model based on Deep Learning ideas.But a neural network that is used here is rather shallow(consists of only one hidden layer).
Behind the scenes we are actually training a simple neural network with a single hidden layer.But we are actually not going to use the neural network after training.Instead,the goal is to learn the weights of the hidden layer.These weights are essentially the word vectors that we're trying to learn.
结论:
word2Vec输出的向量实际是其背后三层神经网络隐藏层的加权值
参考:How to get started with Word2Vec — and then how to make it work (freecodecamp.org)