Greek Stemmer

This Greek Stemmer is the MSc Thesis of Georgios Ntais, entitled “Development of a Stemmer for the Greek Language”. The work was conducted in the Department of Computer and Systems Sciences at University of Stockholm / Royal Institute of Technology.

The system takes as input a word and removes its inflexional suffix according to a rule based algorithm. The algorithm follows the known Porter algorithm for the English language and it is developed according to the grammatical rules of the Modern Greek language.

The current page is an adaptation of the original page and is provided for demonstration. Go ahead and give it a try:

Give a word in GREEK CAPITAL LETTERS and submit to get its stem:

If you want to extract stems at a higher rate, an http service has been created by Fotis Kokkoras. This service provides better automation by supporting either GET or POST calls (in UTF-8) and extraction friendly results (comma separeted, plain text stems).

For example, using http GET calls, you can directry use it like this:

  • http://deixto.com/gr-stemmer.php?clientID=<someID>&input=ΔΡΟΜΕΑΣ,ΝΙΚΗΤΕΣ,ΓΡΗΓΟΡΟΣ
  • Try here the above example (with 12 sec delay).

Note: Due to heavy use, we have stopped accepting anonymmous calls to this service, since 2015-04-10. If you want to make automated use, please contact us and ask for a clientID.

In case you have been provided with a clientID and use this service in your project, please drop a comment regarding your use in our testimonials page.

 

Related Sources


Fatal error: Call to undefined function the_social_widgets() in /nfs/c08/h04/mnt/124752/domains/deixto.com/html/wp-content/themes/deixto/my-stemmer.php on line 584