kazu.steps.document_post_processing.abbreviation_finder

Classes

AbbreviationFinderStep

Detects abbreviations using the algorithm in "A simple algorithm for identifying abbreviation definitions in biomedical text.", (Schwartz & Hearst, 2003).

class kazu.steps.document_post_processing.abbreviation_finder.AbbreviationFinderStep

Bases: Step

Detects abbreviations using the algorithm in “A simple algorithm for identifying abbreviation definitions in biomedical text.”, (Schwartz & Hearst, 2003).

Uses a modified version of the scispacy abbreviation finder rules, to expand abbreviations (see kazu.utils.abbreviation_detector.KazuAbbreviationDetector). In this implementation, abbreviations learnt in one section will be applied throughout the others.

__call__(doc)

Parameters:

• doc (Document)

• self (Self)

Returns:

Return type:

tuple[list[Document], list[Document]]

__init__(exclude_abbrvs=None)

Parameters:

exclude_abbrvs (list[str] | None)