Skip to content

LeonieWeissweiler/CISTEM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CISTEM

license

CISTEM is a stemming algorithm for the German language, developed by Leonie Weißweiler and Alexander Fraser. This repository contains official implementations in a variety of programming languages. At the moment, the following languages are available:

  • Python
  • Java
  • C++
  • C
  • Javascript
  • Go
  • Haskell
  • Perl
  • Swift

The code for each language encludes a method for stemming as well as one for segmentation, which returns the stripped suffix as well as the stem.

Performance

We performed a comparative analysis of six publicly available German stemmers, where CISTEM achieved the best results for f-measure and state-of-the-art results for runtime.

Gold standards

The gold_standards folder contains the two gold standards we used for evaluation. Each file is utf-8 text file with each line containing all the stems of one cluster separated by a single space. Note that we do not supply a reference stem for each cluster, as we measure stemming performance as the ability to group words with the same meaning, which is more relevant for information retrieval purposes than the absolute stem. If you use these gold standards in your own research, please cite our paper: Bibtex

More information on how we evaluated runtimes and stemming quality can be found in our paper:

Leonie Weißweiler, Alexander Fraser (2017). Developing a Stemmer for German Based on a Comparative Analysis of Publicly Available Stemmers. In Proceedings of the German Society for Computational Linguistics and Language Technology (GSCL), to appear.