{
'module' => {
'name' => 'Russian pre-processing',
'submodules' => [
'pre/ru/tagHunPos',
'pre/ru/malt',
],
'submodule names' => [
'POS tagger (hunpos)',
'dependency parser (malt)',
],
'stdout' => 'text',
},
'description' => 'This is the pre-processing module for Italian
corpora. It includes a basic XML markup tool, a general sentence
splitter, and the <a href="http:/www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html">TreeTagger</a>
for Italian which also does tokenization
and lemmatization',
'input' => {
'text' => {
'format' => 'xml',
'root' => 's',
}
},
'output' => {
'text' => {
'format' => 'xml',
'root' => 's',
'write_mode' => 'overwrite',
'status' => 'tag'
}
},
'arguments' => {
'shortcuts' => {
'in' => 'input:text:file',
'out' => 'output:text:file',
'ci' => 'input:text:encoding',
'co' => 'output:text:encoding',
}
},
'widgets' => {
'input' => {
'text' => {
'stream name' => 'stream(format=text,language=it)'
},
},
}
}