adbar/simplemma
Simple multilingual lemmatizer for Python, especially useful for speed and efficiency
Operates on pre-built morphological dictionaries covering 49 languages, enabling lemmatization without morphosyntactic tagging or external dependencies. Features optional greedy decomposition for handling affixes and compound words, chainable language fallbacks for improved coverage, and built-in tokenization with a `lang_detector()` function for automatic language identification. Pure Python implementation with minimal footprint makes it suitable for low-resource environments, educational use, or baseline NLP systems.
188 stars and 59,856 monthly downloads. Used by 2 other packages. No commits in the last 6 months. Available on PyPI.
Stars
188
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jun 06, 2025
Monthly downloads
59,856
Commits (30d)
0
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/adbar/simplemma"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
hplt-project/sacremoses
Python port of Moses tokenizer, truecaser and normalizer
winkjs/wink-porter2-stemmer
Javascript Implementation of Porter Stemmer Algorithm V2 by Dr Martin F Porter
sorenlind/lemmy
🤘Lemmy is a lemmatizer for Danish 🇩🇰 and Swedish 🇸🇪
htaghizadeh/PersianStemmer-Python
PersianStemmer-Python
Blake-Madden/OleanderStemmingLibrary
Porter stemming library (C++)