Word2Vec

Word2vec is a technique in natural language processing for obtaining vector representations of words, capturing information about a word's meaning based on the words surrounding it, following the principles of distributional semantics. Once trained, the resulting model can find words with similar meanings or usage, and its embeddings can serve as inputs to systems for search and classification. Word2vec was developed by Tomas Mikolov, Kai Chen, Greg Corrado, Ilya Sutskever and Jeff Dean at Google, published in preprints and presented at ICLR in 2013; its computational efficiency made it practical to learn high-quality word embeddings from very large text corpora, contributing to widespread adoption across natural language processing.