{
'module' => {
'name' => 'Japanese pre-processing',
'submodules' => [
'pre/markup',
'pre/sent',
'pre/ja/toktag',
],
'submodule names' => [
'basic XML markup',
'sentence splitter',
'Japanese tokenizer+tagger',
],
'stdin' => 'text',
'stdout' => 'text',
},
'description' => 'This is the pre-processing module for Swedish
corpora. It includes a basic XML markup tool, a general sentence
splitter, and the morphological analyzer
<a href="http:/chasen.aist-nara.ac.jp/">ChaSen</a> for tokenization
and some other linguistic markup.',
'input' => {
'text' => {
'format' => 'text',
}
},
'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=ja)'
},
},
}
}