NB: BCS (Serbo-Croatian) tagger covers approximately 80% of an average newspaper text, Polish and Russian tagger cover about 50% of an average newspaper text. This means that in the remaining 20% and 50% of the text one can encounter inconsistencies in the equivalents and/or inflected forms.
Polish tagger, student feedback in the course of the project, summer of 2006
Russian tagger, student feedback in the course of the project, fall of 2006
Experimental version with Russian, Polish, BCS, Mandarin Chinese, and English Tagger
Russian, Polish, and BCS Lemmatizer
Central to this project was the development of the three tagges for Slavic languages. These taggers are intended to enable early inclusion of authentic materials in language learning. A student can paste any text into the tagger and have most words tagged with their English equivalets.
