NEWS (2013-10-13): New release. This page describes the new version of TRmorph and provides a simple demo below. The web page for the old analyzer can be found here.
TRmorph is a relatively complete finite-state morphological analyzer for Turkish. The current version of the analyzer is licensed under the terms of GNU LGPL, and the complete source code can be obtained from GitHub. Please see the documentation for further information.
The analyzer and associated toolas are in active development, and any comments or corrections are welcome.
If you use this analyzer in your research, please cite the relevant paper(s) listed below:
- (2014) A Set of Open Source Tools for Turkish Natural Language Processing In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) Ed. by N. Calzolari et al. 1079–1086 [pdf] [bib]
- (2010) A Freely Available Morphological Analyzer for Turkish In: Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC 2010) 820–827 [pdf] [bib]
TRmorph demo
You can try the current development version (as of 2014-01-16) of TRmorph here. If you have javascript enabled you can use the buttons below the input box to enter special Turkish characters. The analysis symbols are described in the manual. The stems are linked to their Wiktionary definitions.
Some characters in the input string are filtered out in the web demo. If the demo fails to accept the input you provide, or if you need to analyze large amount of data, please download and use an off-line version.
The analyses are ranked according to a sipmple no-context disambiguator, the most likely analysis should be on top.
If things do not look as they should, please let me know.