Skip to main content

An PyTorch CRF implementation extracted from AllenNLP

Project description

#AllenCRF A full features CRF for PyTorch extracted from the AllenNLP Framework

Docs

See the AllenNLP documentation about CRF for full API docs.

Why

The CRF implementation in the AllenNLP framework is very good and easy to use. It notably has a convenient API for specifying allowed (and thus forbidden) transitions.

We extracted the CRF implementation from the framework, so that we can use it without the other dependencies that AllenNLP includes.

Credits

The original implementation was written by Joel Grus with ongoing work from the good folks at AllenNLP.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

allencrf-1.0.2.tar.gz (9.3 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page