finalfrontier

Train/use word embeddings with subword units

6 releases (breaking)

✓ Uses Rust 2018 edition

0.5.0 Apr 25, 2019
0.4.1 Apr 12, 2019
0.4.0 Mar 11, 2019
0.3.0 Jan 29, 2019
0.1.0 Sep 10, 2018

#1 in #embeddings

48 downloads per month
Used in 1 crate

Apache-2.0

119KB
3K SLoC

Crate Docs Build Status

finalfrontier

Introduction

finalfrontier is a Rust library and set of utilities for learning and using word embeddings. finalfrontier currently has the following features:

  • Models:
    • skip-gram (Mikolov et al., 2013)
    • structured skip-gram (Ling et al., 2015)
    • dependency (Levy and Goldberg, 2014)
  • Noise contrastive estimation (Gutmann and Hyvärinen, 2012)
  • Subword representations (Bojanowski et al., 2016)
  • Hogwild SGD (Recht et al., 2011)

This is an early release of finalfrontier, we are planning to add more features in the future. The trained embeddings are stored in finalfusion format, which can be read and used with the finalfusion crate and the finalfusion Python module.

Where to go from here

Dependencies

~5.5MB
~102K SLoC