spaCy/website/docs/api/lemmatizer.md

title	tag	source	new	teaser	api_base_class	api_string_name	api_trainable
Lemmatizer	class	spacy/pipeline/lemmatizer.py	3	Pipeline component for lemmatization	/api/pipe	lemmatizer	false

Component for assigning base forms to tokens using rules based on part-of-speech tags, or lookup tables. Functionality to train the component is coming soon. Different Language subclasses can implement their own lemmatizer components via language-specific factories. The default data used is provided by the spacy-lookups-data extension package.

As of v3.0, the Lemmatizer is a standalone pipeline component that can be added to your pipeline, and not a hidden part of the vocab that runs behind the scenes. This makes it easier to customize how lemmas should be assigned in your pipeline.

If the lemmatization mode is set to "rule", which requires coarse-grained POS (Token.pos) to be assigned, make sure a Tagger, Morphologizer or another component assigning POS is available in the pipeline and runs before the lemmatizer.

Config and implementation

The default config is defined by the pipeline component factory and describes how the component should be configured. You can override its settings via the config argument on nlp.add_pipe or in your config.cfg for training. For examples of the lookups data format used by the lookup and rule-based lemmatizers, see spacy-lookups-data.

Example

config = {"mode": "rule"}
nlp.add_pipe("lemmatizer", config=config)

Setting	Description
mode	The lemmatizer mode, e.g. "lookup" or "rule". Defaults to lookup if no language-specific lemmatizer is available (see the following table). str
overwrite	Whether to overwrite existing lemmas. Defaults to False. bool
model	Not yet implemented: the model to use. Model

Many languages specify a default lemmatizer mode other than lookup if a better lemmatizer is available. The lemmatizer modes rule and pos_lookup require token.pos from a previous pipeline component (see example pipeline configurations in the pretrained pipeline design details) or rely on third-party libraries (pymorphy2).

Language	Default Mode
bn	rule
ca	pos_lookup
el	rule
en	rule
es	rule
fa	rule
fr	rule
it	pos_lookup
mk	rule
nb	rule
nl	rule
pl	pos_lookup
ru	pymorphy2
sv	rule
uk	pymorphy2

%%GITHUB_SPACY/spacy/pipeline/lemmatizer.py

Lemmatizer.__init__

Example

# Construction via add_pipe with default model
lemmatizer = nlp.add_pipe("lemmatizer")

# Construction via add_pipe with custom settings
config = {"mode": "rule", "overwrite": True}
lemmatizer = nlp.add_pipe("lemmatizer", config=config)

Create a new pipeline instance. In your application, you would normally use a shortcut for this and instantiate the component using its string name and nlp.add_pipe.

Name	Description
vocab	The shared vocabulary. Vocab
model	Not yet implemented: The model to use. Model
name	String name of the component instance. Used to add entries to the losses during training. str
keyword-only
mode	The lemmatizer mode, e.g. "lookup" or "rule". Defaults to "lookup". str
overwrite	Whether to overwrite existing lemmas. ~~bool~

Lemmatizer.__call__

Apply the pipe to one document. The document is modified in place, and returned. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order.

Example

doc = nlp("This is a sentence.")
lemmatizer = nlp.add_pipe("lemmatizer")
# This usually happens under the hood
processed = lemmatizer(doc)

Name	Description
doc	The document to process. Doc
RETURNS	The processed document. Doc

Lemmatizer.pipe

Apply the pipe to a stream of documents. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order.

Example

lemmatizer = nlp.add_pipe("lemmatizer")
for doc in lemmatizer.pipe(docs, batch_size=50):
    pass

Name	Description
stream	A stream of documents. Iterable[Doc]
keyword-only
batch_size	The number of documents to buffer. Defaults to 128. int
YIELDS	The processed documents in order. Doc

Lemmatizer.initialize

Initialize the lemmatizer and load any data resources. This method is typically called by Language.initialize and lets you customize arguments it receives via the [initialize.components] block in the config. The loading only happens during initialization, typically before training. At runtime, all data is loaded from disk.

Example

lemmatizer = nlp.add_pipe("lemmatizer")
lemmatizer.initialize(lookups=lookups)

### config.cfg
[initialize.components.lemmatizer]

[initialize.components.lemmatizer.lookups]
@misc = "load_my_lookups.v1"

Name	Description
get_examples	Function that returns gold-standard annotations in the form of Example objects. Defaults to None. Optional[Callable], Iterable[Example]
keyword-only
nlp	The current nlp object. Defaults to None. Optional[Language]
lookups	The lookups object containing the tables such as "lemma_rules", "lemma_index", "lemma_exc" and "lemma_lookup". If None, default tables are loaded from spacy-lookups-data. Defaults to None. Optional[Lookups]

Lemmatizer.lookup_lemmatize

Lemmatize a token using a lookup-based approach. If no lemma is found, the original string is returned.

Name	Description
token	The token to lemmatize. Token
RETURNS	A list containing one or more lemmas. List[str]

Lemmatizer.rule_lemmatize

Lemmatize a token using a rule-based approach. Typically relies on POS tags.

Name	Description
token	The token to lemmatize. Token
RETURNS	A list containing one or more lemmas. List[str]

Lemmatizer.is_base_form

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

Name	Description
token	The token to analyze. Token
RETURNS	Whether the token's attributes (e.g., part-of-speech tag, morphological features) describe a base form. bool

Lemmatizer.get_lookups_config

Returns the lookups configuration settings for a given mode for use in Lemmatizer.load_lookups.

Name	Description
mode	The lemmatizer mode. str
RETURNS	The required table names and the optional table names. Tuple[List[str], List[str]]

Lemmatizer.to_disk

Serialize the pipe to disk.

Example

lemmatizer = nlp.add_pipe("lemmatizer")
lemmatizer.to_disk("/path/to/lemmatizer")

Name	Description
path	A path to a directory, which will be created if it doesn't exist. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
exclude	String names of serialization fields to exclude. Iterable[str]

Lemmatizer.from_disk

Load the pipe from disk. Modifies the object in place and returns it.

Example

lemmatizer = nlp.add_pipe("lemmatizer")
lemmatizer.from_disk("/path/to/lemmatizer")

Name	Description
path	A path to a directory. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
exclude	String names of serialization fields to exclude. Iterable[str]
RETURNS	The modified Lemmatizer object. Lemmatizer

Lemmatizer.to_bytes

Example

lemmatizer = nlp.add_pipe("lemmatizer")
lemmatizer_bytes = lemmatizer.to_bytes()

Serialize the pipe to a bytestring.

Name	Description
keyword-only
exclude	String names of serialization fields to exclude. Iterable[str]
RETURNS	The serialized form of the Lemmatizer object. bytes

Lemmatizer.from_bytes

Load the pipe from a bytestring. Modifies the object in place and returns it.

Example

lemmatizer_bytes = lemmatizer.to_bytes()
lemmatizer = nlp.add_pipe("lemmatizer")
lemmatizer.from_bytes(lemmatizer_bytes)

Name	Description
bytes_data	The data to load from. bytes
keyword-only
exclude	String names of serialization fields to exclude. Iterable[str]
RETURNS	The Lemmatizer object. Lemmatizer

Attributes

Name	Description
vocab	The shared Vocab. Vocab
lookups	The lookups object. Lookups
mode	The lemmatizer mode. str

Serialization fields

During serialization, spaCy will export several data fields used to restore different aspects of the object. If needed, you can exclude them from serialization by passing in the string names via the exclude argument.

Example

data = lemmatizer.to_disk("/path", exclude=["vocab"])

Name	Description
vocab	The shared Vocab.
lookups	The lookups. You usually don't want to exclude this.