4 packages returned for Tags:"embeddings"

Catalyst is a Natural Language Processing library built from scratch for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

C# implementation of "Uniform Manifold Approximation and Projection" (UMAP) for embedding projections.

Package containing a word2vec object for fast nearest neighbors search. Saving and loading format are compatible with python's gensim module.

Integration for Catalyst to run spaCy models from C#.