Welcome to STeP-1 Home page
STeP-1 is the first step in processing Persian language written texts. It performs tokenization, morphological analysis, POS tagging and optional spell checking. Users can select arbitrary combination of these services in different depths for their own task and application.
The first version of Tokenizer and Stemmer sub-systems are now available online. You can select them from right menu.
Send us your suggestions and report system's bugs, so we can improve STeP-1.
NLP Research Laboratory,
Faculty of Electrical and Computer Engineering,
Shahid Beheshti University,