Crosstem Documentation
A comprehensive Python package for morphological analysis combining derivational stemming, inflectional analysis, and cross-lingual etymology.
Why Crosstem?
Crosstem finds true linguistic roots across part-of-speech boundaries, which is something traditional stemmers and lemmatizers cannot do.
Quick Start
Installation:
pip install crosstem
Basic Usage:
from crosstem import DerivationalStemmer
stemmer = DerivationalStemmer('eng')
print(stemmer.stem('organization')) # Output: organize
print(stemmer.stem('beautiful')) # Output: beauty
Key Features
Cross-POS derivational stemming: Only library that finds roots across parts of speech
Linguistic accuracy: Uses MorphyNet morphological data, not brittle rules
Rust-accelerated derivational engine: PyO3 backend with automatic Python fallback
10×+ faster than Porter: Fast graph traversal with hash lookups
Etymology tracing: 4.2M relationships across 2,265 languages
Word families: Discover complete derivational networks
Hybrid runtime: Rust acceleration when available, pure-Python compatibility fallback
15 languages: Multilingual morphology support