Word2vec targets exactly what John Rupert Firth famously said:
"A word is known by the company it keeps."
It is a model that enables the building of word vectors using contextual information from the neighborhood of a word. For every word whose embedding is developed, it's based on the words around it. Word2vec uses a simple neural network to build this architecture. We’ll discuss the details of neural networks in depth in Chapter 8, From Human Neurons to Artificial Neurons for Text Understanding, onward.
A paper on Word2vec came out in 2013 and was one of the revolutionary findings in the domain of Natural Language Processing (NLP). It was developed by Thomas Mikolov et al. at Google and was later made open source for the community to use and build on. A link to the paper can be found at https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf.
Before we get into the details of Word2vec...