medkit.text.postprocessing#

APIs#

For accessing these APIs, you may use import like this:

from medkit.text.postprocessing import <api_to_import>

Classes:

AttributeDuplicator(attr_labels[, uid])

Annotator to copy attributes from a source segment to its nested segments.

DocumentSplitter(segment_label[, ...])

Split text documents using its segments as a reference.

Functions:

compute_nested_segments(source_segments, ...)

Return source segments aligned with its nested segments.

filter_overlapping_entities(entities)

Filter a list of entities and remove overlaps.
class AttributeDuplicator(attr_labels, uid=None)[source]#

Annotator to copy attributes from a source segment to its nested segments. For each attribute to be duplicated, a new attribute is created in the nested segment

Instantiate the attribute duplicator

Parameters

  • attr_labels (List[str]) – Labels of the attributes to copy

  • uid (str) – Identifier of the annotator

Methods:

run(source_segments, target_segments)

Add attributes from source segments to all nested segments.

set_prov_tracer(prov_tracer)

Enable provenance tracing.

Attributes:

description

Contains all the operation init parameters.
run(source_segments, target_segments)[source]#

Add attributes from source segments to all nested segments. The nested segments are chosen among the target_segments based on their spans.

Parameters

  • source_segments (List[Segment]) – List of segments with attributes to copy

  • target_segments (List[Segment]) – List of segments target

property description: medkit.core.operation_desc.OperationDescription#

Contains all the operation init parameters.

Return type

OperationDescription

set_prov_tracer(prov_tracer)#

Enable provenance tracing.

Parameters

prov_tracer (ProvTracer) – The provenance tracer used to trace the provenance.

compute_nested_segments(source_segments, target_segments)[source]#

Return source segments aligned with its nested segments. Only nested segments fully contained in the source_segments are returned.

Parameters

  • source_segments (List[Segment]) – List of source segments

  • target_segments (List[Segment]) – List of segments to align

Return type

List[Tuple[Segment, List[Segment]]]

Returns

List[Tuple[~medkit.core.text.Segment,List[~medkit.core.text.Segment]]] – List of aligned segments

class DocumentSplitter(segment_label, entity_labels=None, attr_labels=None, relation_labels=None, name=None, uid=None)[source]#

Split text documents using its segments as a reference.

The resulting ‘mini-documents’ contain the entities belonging to each segment along with their attributes.

This operation can be used to create datasets from medkit text documents.

Instantiate the document splitter

Parameters

  • segment_label (str) – Label of the segments to use as references for the splitter

  • entity_labels (Optional[List[str]]) – Labels of entities to be included in the mini documents. If None, all entities from the document will be included.

  • attr_labels (Optional[List[str]]) – Labels of the attributes to be included into the new annotations. If None, all attributes will be included.

  • relation_labels (Optional[List[str]]) – Labels of relations to be included in the mini documents. If None, all relations will be included.

  • name (Optional[str]) – Name describing the splitter (default to the class name).

  • uid (str, Optional) – Identifier of the operation

Methods:

run(docs)

Split docs into mini documents

set_prov_tracer(prov_tracer)

Enable provenance tracing.

Attributes:

description

Contains all the operation init parameters.
run(docs)[source]#

Split docs into mini documents

Parameters

documents – List of text documents to split

Return type

List[TextDocument]

Returns

List of documents created from the selected segments

property description: medkit.core.operation_desc.OperationDescription#

Contains all the operation init parameters.

Return type

OperationDescription

set_prov_tracer(prov_tracer)#

Enable provenance tracing.

Parameters

prov_tracer (ProvTracer) – The provenance tracer used to trace the provenance.

filter_overlapping_entities(entities)[source]#

Filter a list of entities and remove overlaps. This method may be useful for the creation of data for named entity recognition, where a part of text can only contain one entity per ‘word’. When an overlap is detected, the longest entity is preferred.

Parameters

entities (List[Entity]) – Entities to filter

Return type

List[Entity]

Returns

List[Entity] – Filtered entities

Subpackages / Submodules#

medkit.text.postprocessing.alignment_utils

medkit.text.postprocessing.attribute_duplicator

medkit.text.postprocessing.document_splitter

medkit.text.postprocessing.overlapping