TomapTrain
Synopsis
TomapTrain analyzes terms in preparation of the classification of candidates with ToMap .
Description
TomapTrain assumes each sentence or section is a proxy term according to the ToMap method. TomapTrain analyzes the syntactic structure of sections and stores them in outFile . Use this file for classifying terms with TomapProjector . The identifier associated with the proxy is specified with conceptIdentifier .
Snippet
<tomaptrain class="TomapTrain">
<conceptIdentifier></conceptIdentifier>
<outFile></outFile>
<rcFile></rcFile>
<yateaExecutable></yateaExecutable>
</tomaptrain>
Mandatory parameters
conceptIdentifier
An expression evaluated as a string from the section or sentence that specifies the identifier associated with the proxy.
outFile
Path to the file where to store the proxy syntactic structures and associated identifiers/
rcFile
Path to the YaTeA configuration file.
yateaExecutable
Path to the YaTeA executable file.
Optional parameters
configDir
language
localeDir
outputDir
perlLib
Contents of the PERLLIB in the environment of Yatea binary.
postProcessingConfig
BioYaTeA option: path to the post-processing file option.
postProcessingOutput
BioYaTeA option: path to the result file after post-processing.
suffix
termListFile
Path where to write the candidates list produced by YaTeA.
xmlTermsFile
Path where to write the candidates XML file produced by YaTeA.
bioYatea
documentFilter
UNDOCUMENTED
formFeature
Feature containing the word form.
lemmaFeature
Feature containing the word lemma.
posFeature
Feature containing the word POS tag.
sectionFilter
UNDOCUMENTED
sentenceLayer
Name of the layer containing sentence annotations, sentences are reinforced.
wordLayer
Name of the layer containing the word annotations.
yateaDefaultConfig
yateaOptions
Deprecated parameters
sentenceLayerName
Deprecated alias for sentenceLayer .
wordLayerName
Deprecated alias for wordLayer .
workingDir
Path to the directory where YaTeA is launched. This parameter is deprecated , use xmlTermsFile and termListFile instead.