AlvisNLP

corpus processing engine

TEESClassify

Synopsis

Classify binary relations with the TEES Classifier based on trained model.

Description

Snippet

<teesclassify class="TEESClassify">
    <namedEntityLayer></namedEntityLayer>
    <python2Executable></python2Executable>
    <schema></schema>
    <teesHome></teesHome>
    <teesModel></teesModel>
</teesclassify>

Mandatory parameters

namedEntityLayer

Mandatory
Type: String

Name of the layer containing the named entities.

python2Executable

Mandatory

Path to the Python 2 executable, TEES will fail if run through Python 3.

schema

Mandatory

Give the schema of the relations to train i.e.


      	  <schema>
	    <Lives_In>Bacteria,Location</Lives_In>
      	  </schema>
	

teesHome

Mandatory

Path to the TEES home directory.

teesModel

Mandatory
Type: InputFile

Path to the trained model to use. Pre-trained models for BB16 and Seedev16 are available in /alvisnlp-bibliome/src/main/resources/fr/inra/maiage/bibliome/alvisnlp/bibliomefactory/resources/tees-models

Optional parameters

constantRelationFeatures

Optional
Type: Mapping

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

constantTupleFeatures

Optional
Type: Mapping

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

dependencyLabelFeature

Default value: `label`
Type: String

Feature where to store the dependency label.

dependencyRelation

Default value: `dependencies`
Type: String

UNDOCUMENTED

dependentRole

Default value: `dependent`
Type: String

UNDOCUMENTED

documentFilter

Default value: `true`
Type: Expression

Only process document that satisfy this expression.

headRole

Default value: `head`
Type: String

UNDOCUMENTED

namedEntityTypeFeature

Default value: `ne-type`
Type: String

Name of the feature to access the type of the named entities.

omitSteps

Default value: `GENIA_SPLITTER,BANNER`
Type: String

Set the preprocessing steps to ignore in the form of [GENIA_SPLITTER][,BANNER][,BLLIP_BIO][,STANFORD_CONVERT][,SPLIT_NAMES][,FIND_HEADS]

posFeature

Default value: `pos`
Type: String

Name of the feature containing the POS-tag.

sectionFilter

Default value: `true and layer:words and layer:sentences`
Type: Expression

Process only sections that satisfy this expression.

sentenceLayer

Default value: `sentences`
Type: String

Name of the layer that contains sentence annotations.

sentenceRole

Default value: `sentence`
Type: String

UNDOCUMENTED

tokenLayer

Default value: `words`
Type: String

Name of the layer that contains tokens.

Deprecated parameters

dependencyLabelFeatureName

Deprecated
Type: String

Deprecated alias for dependencyLabelFeature .

dependencyRelationName

Deprecated
Type: String

Deprecated alias for dependencyRelation .

namedEntityLayerName

Deprecated
Type: String

Deprecated alias for namedEntityLayer .

sentenceLayerName

Deprecated
Type: String

Deprecated alias for sentenceLayer .

tokenLayerName

Deprecated
Type: String

Deprecated alias for tokenLayer .