vokab

vokab is a python module for storing, searching and matching named entities on their name or aliases. This project is useful for auto-correcting or linking named entities in NLP information extraction use cases or when cleaning up user submitted data.

Supports:

• Exact Matching
• Case-insensitive Matching
• Lexical Matching (i.e. Fuzzy String Matching)
• Semantic Matching (i.e. Vector Similarity Searching)
• Hybrid (Lexical/Fuzzy + Semantic/Vector)

Getting Started

Installation

Available on PyPI:

pip install vokab

Maintainer

vokab was created by Ian Maurer, the CTO of GenomOncology.

This MIT-based open-source project was extracted from our product which includes the ability to normalize biomedical data for use in precision oncology clinical decision support systems. Contact me to learn more about our product offerings.