top | item 18914427

(no title)

mlucy | 7 years ago

I would second this; sentence embeddings outperform word embeddings on basically all tasks where you actually have sentences to work with. The only downside is that they're significantly more computationally intensive, especially for Transformer models like BERT.

(Note: I'm fairly biased, since I work on https://www.basilica.ai, which among other things makes sentence embeddings available over a REST interface.)

discuss

order

No comments yet.