Skip to main content

How does Wordbee deal with morphology?


How does Wordbee deal with morphology?


Terminology and translation memory lookups leverage a morphological engine. This is implemented with language specific stemming in currently 32 languages. For all other languages a default suffix-only stemming is applied, in conjunction with the regular non-stemmed analysis of text. Decomposition is implemented to some limited extent at a higher layer for the calculation of the hit similarity percentage. It shall be noted that CJK languages are tokenized with CJK specific mechanisms (and not using stemming but decomposition).

Language specific stemming is supported for:

  • arabic

  • armenian

  • basque

  • bulgarian

  • catalan

  • cjk

  • czech

  • danish

  • dutch

  • english

  • finnish

  • french

  • galician

  • german

  • greek

  • hindi

  • hungarian

  • indonesian

  • irish

  • italian

  • latvian

  • lithuanian

  • norwegian

  • persian

  • portuguese

  • romanian

  • russian

  • sorani

  • spanish

  • swedish

  • thai

  • turkish

Learn more

Supported languages

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.