spaCy/spacy/lang/nb/lemmatizer/_lemma_rules.py
Knut O. Hellan a54f0cfc2b Norwegian tweaks (#3894)
* Norwegian fix

Add support for alternative past tense verb form (vaska).

* Norwegian months

Add all Norwegian months to tokenizer excpetions.

* More Norwegian abbreviations

Add more Norwegian abbreviations to tokenizer_exceptions.

* Contributor agreement khellan

Add signed contributor agreement for khellan (Knut O. Hellan).
2019-07-08 10:28:47 +02:00

33 lines
661 B
Python

# coding: utf8
from __future__ import unicode_literals
ADJECTIVE_RULES = [
["e", ""], # pene -> pen
["ere", ""], # penere -> pen
["est", ""], # penest -> pen
["este", ""], # peneste -> pen
]
NOUN_RULES = [
["en", "e"], # hansken -> hanske
["a", "e"], # veska -> veske
["et", ""], # dyret -> dyr
["er", "e"], # hasker -> hanske
["ene", "e"], # veskene -> veske
]
VERB_RULES = [
["er", "e"], # vasker -> vaske
["et", "e"], # vasket -> vaske
["a", "e"], # vaska -> vaske
["es", "e"], # vaskes -> vaske
["te", "e"], # stekte -> steke
["år", "å"], # får -> få
]
PUNCT_RULES = []