ChristophAlt/pytorch-starspace

PyTorch implementation of StarSpace as described in "StarSpace: Embed All The Things!" by Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes and Jason Weston

28
/ 100
Experimental

This helps machine learning engineers or researchers working with PyTorch to train models that understand relationships between different types of data, such as text documents. You provide a dataset of various items, and it generates numerical representations (embeddings) that capture their semantic similarities. This allows for tasks like classifying news articles or finding related content.

No commits in the last 6 months.

Use this if you are a machine learning practitioner looking for a PyTorch-based tool to create embeddings that connect diverse data types, especially for text analysis or recommendation systems.

Not ideal if you need a fully featured, production-ready StarSpace implementation, as this version is still under development and does not yet match the original C++ functionality.

natural-language-processing machine-learning-engineering text-classification data-embedding recommendation-systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

52

Forks

6

Language

Python

License

Last pushed

Apr 24, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ChristophAlt/pytorch-starspace"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.