Morphological stemming in RapidMiner?

batstache611batstache611 Member Posts: 45 Guru
edited December 2018 in Help

Hi All,

Instead of using the Porter stemming algo or one of its variants, is it possible to stem words to their morphological root in RapidMiner?

 

Thank you.

Tagged:

Answers

  • pschlunderpschlunder Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, RMResearcher, Member Posts: 96 RM Research

    Hi,

    two options you might want to try include two new operators present in the Operator Toolbox extension.

    One option includes using the Stem Tokens Using ExampleSet-Operator using a predefined ExampleSet as a source of potential word stems (similar to the Stem (Dictionary) operator, but using an ExampleSet as an input instead of a file). You'll find an example process included as a tutorial.

    Another option would be trying to use the Levenshtein Distance. With it you could search for token with a low Levenshtein Distance and choose the shortest of them. You'll find a Generate Levenshtein Distance-Operator in the Operator Toolbox as well.

     

    Best,

    Philipp

Sign In or Register to comment.