Train a new sentence detector from the training data in the first file
and write the model to the second file.
The training data file is expected to have one sentence per line.
Simple tests of TextModification
Output expected:
UNSUPPORTED: TextModification with offset changes.
UNSUPPORTED: TextModification with offset changes.
UNSUPPORTED: TextModification with offset changes.
Orig: Non Hodgkin's the x ray without any non small cell complications.
New: (new text not generated, see previous messages)
Non-Hodgkin Orig: 0-12 New: 0-11
x-ray Orig: 19-25 New: 18-23
non-small-cell Orig: 38-53 New: 36-50
Orig: Non Hodgkin's the x ray without any non small cell complications.
New: Non-Hodgkin's the x-ray without any non-small-cell complications.
Non-Hodgkin Orig: 0-11 New: 0-11
x-ray Orig: 18-23 New: 18-23
non-small-cell Orig: 36-50 New: 36-50
Note the case of the words doesn't matter.
Read a file containing POS-tagged tokens in OpenNLP format,
and output a tagDictionary (OpenNLP format)
Example input:
winning_JJ body_NN
winning_VBG
Example output:
body NN
winning JJ VBG
keywordsFile and stopwordsFile must point to the files in the resources
dataFile is your own sentence-level data in the format (class_label: C,
P, S): sentence|class_label sentence|class_label ...
Equivalent to cTAKES: edu.mayo.bmi.uima.cdt.type.MeasurementAnnotation
Updated by JCasGen Tue Apr 09 11:44:44 EDT 2013
XML source:apache-ctakes-3-0-0/ctakes-pad-term-spotter/src/main/resources/org/apache/ctakes/padtermspotter/types/TypeSystem.xml
The amount of time after which a medication should stop being used, e.g., "2 weeks" in "one 5 mg tablet twice-a-day for 2 weeks"
Updated by JCasGen Tue Apr 09 11:44:34 EDT 2013
XML source:apache-ctakes-3-0-0/ctakes-pad-term-spotter/src/main/resources/org/apache/ctakes/padtermspotter/types/TypeSystem.xml
The amount of time after which a medication should stop being used, e.g., "2 weeks" in "one 5 mg tablet twice-a-day for 2 weeks"
Updated by JCasGen Tue Apr 09 11:44:34 EDT 2013