The SET project

The SET (Syntactic Engineering Tool) project aims to develop a new approach to syntactic analysis of the Czech language. The new method is based on pattern matching linking rules. SET can be viewed as a tool for automatic syntactic analysis of the Czech language and for development of rule-based formalisms for syntactic analysis of natural languages. The included formalisms are based on detection of important items in the input sentence and incremental segmentation of the sentence. The SET system is being developed at NLP Centre at Faculty of Informatics, Masaryk University in Brno and can be copied and distributed under the GNU General Public License version 3.

More information:


Feb 13, 2023 version 0.8.2 available for download
Apr 5, 2016 version 0.8.1 available for download
Nov 5, 2015 version 0.8 available for download
May 25, 2014 Dissertation (partly) on SET made public
May 25, 2014 version 0.7 available for download
Dec 10, 2012 version 0.6 available for download
Dec 8, 2012 support for phrasal verbs
Jul 20, 2012 first version of English grammar published in the git repository
Apr 5, 2012 changed format of the grammar (see documentation)
Aug 18, 2011 wwwSET web interface to the analyser activated
Aug 18, 2011 Version 0.5.1 available for download
Feb 18, 2010 Version 0.4 available for download

This software was developed at the Natural Language Processing Centre, Faculty of Informatics, Masaryk University in Brno with a financial support from the Czech Science Foundation under the project P401/10/0792 and from the Ministry of Education of CR within the LINDAT-Clarin project LM2010013.

If you use the system, please mention this web page and cite this paper in your work. If you are using the punctuation detection for Czech built into the parser, please cite also this paper.

Last modified 5 months ago Last modified on Nov 5, 2023, 9:16:47 PM