Skip to main content

Framework for build NLP information extraction systems using regular expressions.

Project description

konsepy

Framework for build NLP information extraction systems using regular expressions. konsepy then enables leveraging the NLP system to create a silver standard for fine-tuning a transformer model.

Installation

  • konsepy is designed to be used with the knosepy_nlp_template
    • See the README there for current installation instructions.
  • To use konsepy as a standalone entity:
    • Install with pip:
      • pip install konsepy[all]
      • For sentence-splitting corpora from fine-tuning a sentence based transformer, spacy will also need to be installed and configured.

Usage

For now, find documentation for this library (and a template to download) from https://github.com/kpwhri/konsepy_nlp_template.

Roadmap

  • Change labels to some metadata object to allow more diverse input sources and run info

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

konsepy-0.1.0.tar.gz (18.8 kB view details)

Uploaded Source

Built Distribution

konsepy-0.1.0-py3-none-any.whl (23.1 kB view details)

Uploaded Python 3

File details

Details for the file konsepy-0.1.0.tar.gz.

File metadata

  • Download URL: konsepy-0.1.0.tar.gz
  • Upload date:
  • Size: 18.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for konsepy-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5608599c2f53fe9da7cc94de66cb286145b13fed6a2b509fba41ff2b674b2a1f
MD5 a58626cd23b590236a8526fe62a087c3
BLAKE2b-256 af7bab348c33563e51c21e39b8fabcfdbe3979eaa6e167132660918fea5f9ade

See more details on using hashes here.

File details

Details for the file konsepy-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: konsepy-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 23.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for konsepy-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 10e6f78b51021d3bbaafbbeb8900d2a09db01fcb9d228502d6c17fae87800991
MD5 c0bc50b693540c72f8c51609d63237e2
BLAKE2b-256 d5273dce531be6f296a114347a69b565c7c84fc292d4c108f3dcaff2a0da98ff

See more details on using hashes here.

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