Python Natural Language Processing

Recall word embedding

We have already covered word embedding in Chapter 5, Feature Engineering and NLP Algorithms. We have looked at language models and feature engineering techniques in NLP, where words or phrases from the vocabulary are mapped to vectors of real numbers. The techniques used to convert words into real numbers are called word embedding. We have been using vectorization, as well as term frequency-inverse document frequency (tf-idf) based vectorization. So, let's just jump into the world of word2vec.