When would you use word2vec over BERT?

I am very new to Machine Learning and I have recently been exposed to word2vec and BERT.

From what I know, word2vec provides a vector representation of words, but is limited to its dictionary definition. This would mean the algorithm may output the unwanted definition of a word with multiple meanings.

BERT on the other hand, is able to use context clues in the sentence to describe the true meaning of the word.

To me, it sounds like BERT would always be the better choice when it comes to identifying the definition of a word.

Could someone explain when word2vec would be more useful?

Topic bert word2vec

Category Data Science

1
answered at

Word2vec is trained on a specific corpus and the lookup runs in constant time.

When you don't want context sensitive embeddings of the word depending upon the surrounding words, you can use word2vec. Word2Vec runs blazingly faster than BERT.

Hence, when your requirement for word embedding is sufficed by word2vec, no over engineer by taking BERT.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.