Text representation isNLPThe mission is very basic and at the same time a very important part. This article will introduce the history of text representation and the advantages and disadvantages of each method.
We'll start with the simplest method and move on to more subtle solutions such as feature engineering, word vectors and deep learning.
Can the embedding of article titles predict popularity? Can we understand the relationship between emotions and stocks?word2vecCan help us answer these questions, and so on.