lookup_lemmatizer

LookupLemmatizer

Bases: Pipe

LookupLemmatizer learn (token, pos, morph. feat) -> lemma mappings during training, and applies them at prediction time.

scorer instance-attribute

scorer = scorer

source instance-attribute

source = source

create staticmethod

create(nlp, name, scorer, source)

from_disk

from_disk(path, exclude=tuple())

initialize

initialize(get_examples, *, nlp=None)

to_disk

to_disk(path, exclude=tuple())

train

train(sentences, min_occurrences=1)

Parameters:

Name	Type	Description	Default
sentences	Iterable[Iterable[Tuple[str, str, str, str]]]	Sentences to learn the mappings from	required
min_occurrences	int	mapping occurring less than this threshold are not learned	1

---

Last update: January 3, 2024