statsmaths/fasttextM: Fast Multilingual Word Embeddings

Provides a set of tools for downloading and applying the fasttext word embeddings. All embeddings are fit in-memory for speed. The resulting embeddings can be used for supervised and unsupervised learning over a text-based corpus. Embeddings are consistent across languages, so similar words in different language should get mapped to similar vectors in the output space.

Getting started

Package details

MaintainerTaylor B. Arnold <>
Package repositoryView on GitHub
Installation Install the latest version of this package by entering the following in R:
statsmaths/fasttextM documentation built on April 2, 2020, 5:33 p.m.