First, you need to compute these embeddings at least once - sparsity, here you a...

First, you need to compute these embeddings at least once - sparsity, here you are! Second, these embeddings may be different between tasks and accuracy from their use may differ too.

For example, the embeddings produced from CBOW and skipgram word2vec models are strikingly different in cosine similarity sense - different classes of words are similar in CBOW and skipgram.