StanfordNER

Synopsis

Applies the Stanford NLP named-entity recognition .

Description

Applies the Stanford NLP named-entity recognition . StanfordNER requires sentence splitting and tokenization.

Snippet

📋

<stanfordner class="StanfordNER">
    <classifierFile></classifierFile>
    <labelFeature></labelFeature>
    <targetLayer></targetLayer>
</stanfordner>

Mandatory parameters

classifierFile

Path to the CRF classifier.

labelFeature

Name of the feature where to store the named entity label.

targetLayer

Name of the layer where to store named-entity annotation.

Optional parameters

constantAnnotationFeatures

Constant features to add to each annotation created by this module.

documentFilter

Only process document that satisfy this expression.

formFeature

Name of the feature containing the token surface form (ignored if searchInContents is set).

searchInContents

If true, then search named entities in the section contents.

sectionFilter

Process only sections that satisfy this expression.

sentenceLayer

Name of the layer containing sentence annotations (ignored if searchInContents is set).

wordLayer

Name of the layer containing token annotations (ignored if searchInContents is set).

Deprecated parameters

formFeatureName

Deprecated alias for formFeature .

labelFeatureName

Deprecated alias for labelFeature .

sentenceLayerName

Deprecated alias for sentenceLayer .

targetLayerName

Deprecated alias for targetLayer .

wordLayerName

Deprecated alias for wordLayer .