Word2vec vs BERT

Both word2vec and BERT are recent popular methods in NLP which are used for generating vector representation of words. Essentially replacing the use of word index dictionaries and one hot encoded vectors to represent text. Both word-index and one hot encoding methods do not capture the semantic sense of language. Also, one hot encoding becomes computationally infeasible if the size of vocabulary is LARGE. Word2vec [1] is a neural network approach to learn distributed word vectors in a way that words used in similar syntactic or semantic context, lie closer to each other in the distributed vector space.