Linker

The linker will link the detected entities to a existing set of labels. Some of the linkers, however, are end-to-end, i.e. they don't need the mentions extractor, as they detect and link the entities at the same time.

There are 6 linkers available currently, 4 of them are end-to-end and 2 are not.

Linker Name	end-to-end	Source Code	Paper
Blink	X	Source Code	Paper
GENRE	X	Source Code	Paper
SMXM	✓	Source Code	Paper
TARS	✓	Source Code	Paper
GLINER	✓	Source Code	Paper
RELIK	✓	Source Code	Paper

Bases: ABC

Linker define a standard interface for entity linking. A Linker may relay on existing extracted mentions or perform end-2-end extraction

entities property

Entities to link to

link(docs, batch_size=None)

Perform the entity linking. Call the predict function and add entities to the Spacy Docs

Parameters:

Name	Type	Description	Default
docs	Iterator[Doc]	A list of spacy Document	required
batch_size	Optional[Union[int, None]]	The batch size	None

Returns:

Type	Description

load_models()

Load the model

Returns:

Type	Description

predict(docs, batch_size=None) abstractmethod

Perform the entity prediction

Parameters:

Name	Type	Description	Default
docs	Iterator[Doc]	A list of spacy Document	required
batch_size	Optional[Union[int, None]]	The batch size	None

Returns:

Type	Description
List[List[Span]]	List Spans for each Document in docs

set_device(device)

Set the device to use

Parameters:

Name	Type	Description	Default
device	Union[str, device]		required

Returns:

Type	Description

set_kg(entities)

Set entities that linker can use

Parameters:

Name	Type	Description	Default
entities	Iterator[Entity]	The list of entities	required