The Tale of Bloom Embeddings and Unseen Entities

The default Bloom embedding layer in spaCy is unconventional, but very powerful and efficient. We wrote about it before and showed the advantages it provides in terms of memory efficiency for our floret embeddings. Now we have released the first technical report by Explosion, where we explain Bloom embeddings in more detail and rigorously compare them to traditional embeddings. In this post we'll highlight some of our results with a special focus on unseen entities.

advantages blog bloom efficiency embedding embeddings layer memory report spacy technical terms