simplemma 0.1.0

Installation

The current library is written in pure Python with no dependencies:

pip install simplemma (or pip3 where applicable)

Usage

Simplemma is used by selecting a language of interest and then applying the data on a list of words.

>>> import simplemma
# decide which language data to load
>>> langdata = simplemma.load_data('de')
# apply it on a word form
>>> simplemma.lemmatize(myword, langdata)
# grab a list of tokens
>>> mytokens = ['Hier', 'sind', 'Tokens']
>>> for token in mytokens:
>>>     simplemma.lemmatize(token, langdata)
'hier'
'sein'
'tokens'
# list comprehensions can be faster
>>> [simplemma.lemmatize(t, langdata) for t in mytokens]
['hier', 'sein', 'tokens']

Chaining several languages can improve coverage:

>>> langdata = simplemma.load_data('de', 'en')
>>> simplemma.lemmatize('Tokens', langdata)
'token'
>>> langdata = simplemma.load_data('en')
>>> simplemma.lemmatize('spaghetti', langdata)
'spaghetti'
>>> langdata = simplemma.load_data('en', 'it')
>>> simplemma.lemmatize('spaghetti', langdata)
'spaghetto'

There are cases for which a greedier algorithm is better. It is activated by default:

>>> langdata = simplemma.load_data('de')
>>> simplemma.lemmatize('angekündigten', langdata)
'ankündigen' # infinitive verb
>>> simplemma.lemmatize('angekündigten', langdata, greedy=False)
'angekündigt' # past participle

Caveats:

# don't expect too much though
>>> langdata = simplemma.load_data('it')
# this diminutive form isn't in the model data
>>> simplemma.lemmatize('spaghettini', langdata)
'spaghettini' # should read 'spaghettino'

Supported languages

The following languages are available using their ISO 639-1 code:

• bg: Bulgarian (low coverage)

• ca: Catalan

• cs: Czech (low coverage)

• cy: Welsh

• de: German (see also this list)

• en: English (alternative: LemmInflect)

• es: Spanish

• fa: Persian (low coverage)

• fr: French

• ga: Irish

• gd. Gaelic

• gl: Galician

• gv: Manx

• hu: Hungarian (low coverage)

• it: Italian

• pt: Portuguese

• ro: Romanian

• ru: Russian (alternative: pymorphy2)

• sk: Slovak

• sl: Slovenian (low coverage)

• sv: Swedish (alternative: lemmy)

• uk: Ukranian (alternative: pymorphy2)

Low coverage mentions means you’d probably be better off with a language-specific library, but simplemma will work to a limited extent. Open-source alternatives for Python are referenced if available.

• Free software: MIT license

• Documentation: https://github.com/adbar/simplemma

Roadmap

• [ ] Integrate further lemmatization lists

• [ ] Function as a meta-package?

• [ ] Integrate optional, more complex models?

Credits

The current version basically acts as a wrapper for lemmatization lists by Michal Měchura (Open Database License). This rule-based approach based on flexion and lemmatizations dictionaries is to this day an approach used in popular libraries such as spacy.

Contributions

Feel free to contribute, notably by filing issues for feedback, bug reports, or links to further lemmatization lists, rules and tests.

You can also contribute to this lemmatization list repository.

Other solutions

See lists: German-NLP and other awesome-NLP lists.

For a more complex but universal approach in Python see universal-lemmatizer.