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)
  • directional skip-gram (Song et al., 2018)
  • dependency (Levy and Goldberg, 2014)
• Noise contrastive estimation (Gutmann and Hyvärinen, 2012)
• Subword representations (Bojanowski et al., 2016)
• Hogwild SGD (Recht et al., 2011)
• Quantized embeddings through the finalfusion quantize command.

The trained embeddings are stored in finalfusion format, which can be read and used with the finalfusion crate and the finalfusion Python module.

The minimum required Rust version is currently 1.40.

Where to go from here

• Installation
• Quickstart
• Manual pages:
  • finalfrontier-skipgram(1) — train word embeddings with the (structured) skip-gram model
  • finalfrontier-deps(1) — train word embeddings with dependency contexts
• finalfusion crate
• Python module