|
396 | 396 | ChoiceParameter('distance','How many edits?','Search a distance of N characters for variants',choices=[('2','Up to two edits'),('1','Only one edit')]) #old TICCL -L |
397 | 397 | ]), |
398 | 398 | ('Automatic Linguistic Enrichment', [ |
399 | | - BooleanParameter('tok','Perform Tokenisation',"Perform tokenisation."), |
400 | | - BooleanParameter('frog','Perform Linguistic Enrichment',"Performs tokenisation, Part-of-Speech tagging, lemmatisation, named entity recognition and more. This is implemented only for Dutch (uses Frog)!!!") |
| 399 | + BooleanParameter('tok','Tokenisation',"Perform tokenisation", default=True), |
| 400 | + BooleanParameter('pos','Part-of-Speech Tagging',"Part-of-speech Tagging (for Dutch only!)",default=True), |
| 401 | + BooleanParameter('lemma','Lemmatisation',"Lemmatisation (for Dutch only!)", default=True), |
| 402 | + BooleanParameter('morph','Morphological Analysis',"Morphological Analysis (for Dutch only!)", default=False), |
| 403 | + BooleanParameter('ner','Named Entity Recognition',"Named Entity Recognition", default=False), |
| 404 | + BooleanParameter('parser','Dependency Parser',"Dependency parser (for Dutch only!)", default=False), |
| 405 | + BooleanParameter('chunker','Chunker / Shallow-parser Parser',"Chunker / Shallow parser (for Dutch only!)", default=False), |
401 | 406 | ]), |
402 | 407 | #('Focus Word Selection', [ |
403 | 408 | # IntegerParameter('minlength','Minimum Word Length','Integer between zero and one hundred',default=5,minvalue=0, maxvalue=100), #old ticcl -x |
|
421 | 426 | ] |
422 | 427 |
|
423 | 428 |
|
424 | | -# ======== DISPATCHING (ADVANCED! YOU CAN SAFELY SKIP THIS!) ======== |
| 429 | +# ======== DISPATCHING (ADVANCED! YOU CAN SAFELY SmedKIP THIS!) ======== |
425 | 430 |
|
426 | 431 | #The dispatcher to use (defaults to clamdispatcher.py), you almost never want to change this |
427 | 432 | #DISPATCHER = 'clamdispatcher.py' |
|
0 commit comments