KeyBERT
Minimal keyword extraction library using BERT embeddings.
About
KeyBERT by Maarten Grootendorst is a minimal keyword and keyphrase extraction library that uses BERT embeddings to find the words and phrases most semantically similar to a document. It supports multiple embedding backends, diversification methods like maximal marginal relevance, and optional large language model integration, with a simple Python API. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Natural Language Processing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Beginner (1/5)
- License
- MIT
- Added
- Apr 3, 2026
Related Tools
Generalist model for named entity recognition using bidirectional transformer.
Language detection library ported from Google language-detection.
Comprehensive NLP toolkit for education and research in Python.
Data protection and PII anonymization framework by Microsoft.
Topic modeling and document similarity library for unsupervised NLP.
Simple framework for state-of-the-art NLP by Zalando Research.