spaCy/website/docs/api/lemmatizer.md

title	teaser	tag	source
Lemmatizer	Assign the base forms of words	class	spacy/lemmatizer.py

The Lemmatizer supports simple part-of-speech-sensitive suffix rules and lookup tables.

Lemmatizer.__init__

Initialize a Lemmatizer. Typically, this happens under the hood within spaCy when a Language subclass and its Vocab is initialized.

Example

from spacy.lemmatizer import Lemmatizer
from spacy.lookups import Lookups
lookups = Lookups()
lookups.add_table("lemma_rules", {"noun": [["s", ""]]})
lemmatizer = Lemmatizer(lookups)

For examples of the data format, see the spacy-lookups-data repo.

Name	Type	Description
lookups 2.2	Lookups	The lookups object containing the (optional) tables "lemma_rules", "lemma_index", "lemma_exc" and "lemma_lookup".
RETURNS	Lemmatizer	The newly created object.

As of v2.2, the lemmatizer is initialized with a Lookups object containing tables for the different components. This makes it easier for spaCy to share and serialize rules and lookup tables via the Vocab, and allows users to modify lemmatizer data at runtime by updating nlp.vocab.lookups.

- lemmatizer = Lemmatizer(rules=lemma_rules)
+ lemmatizer = Lemmatizer(lookups)

Lemmatizer.__call__

Lemmatize a string.

Example

from spacy.lemmatizer import Lemmatizer
from spacy.lookups import Lookups
lookups = Lookups()
lookups.add_table("lemma_rules", {"noun": [["s", ""]]})
lemmatizer = Lemmatizer(lookups)
lemmas = lemmatizer("ducks", "NOUN")
assert lemmas == ["duck"]

Name	Type	Description
string	unicode	The string to lemmatize, e.g. the token text.
univ_pos	unicode / int	The token's universal part-of-speech tag.
morphology	dict / None	Morphological features following the Universal Dependencies scheme.
RETURNS	list	The available lemmas for the string.

Lemmatizer.lookup

Look up a lemma in the lookup table, if available. If no lemma is found, the original string is returned. Languages can provide a lookup table via the Lookups.

Example

lookups = Lookups()
lookups.add_table("lemma_lookup", {"going": "go"})
assert lemmatizer.lookup("going") == "go"

Name	Type	Description
string	unicode	The string to look up.
orth	int	Optional hash of the string to look up. If not set, the string will be used and hashed. Defaults to None.
RETURNS	unicode	The lemma if the string was found, otherwise the original string.

Lemmatizer.is_base_form

Check whether we're dealing with an uninflected paradigm, so we can avoid lemmatization entirely.

Example

pos = "verb"
morph = {"VerbForm": "inf"}
is_base_form = lemmatizer.is_base_form(pos, morph)
assert is_base_form == True

Name	Type	Description
univ_pos	unicode / int	The token's universal part-of-speech tag.
morphology	dict	The token's morphological features.
RETURNS	bool	Whether the token's part-of-speech tag and morphological features describe a base form.

Attributes

Name	Type	Description
lookups 2.2	Lookups	The lookups object containing the rules and data, if available.