Hybrid Lemmatizer for Estonian
Tkachenko Alexander, Petmanson Timo, Laur Sven · Frontiers in artificial intelligence and applications · 2014
In this paper, we present a lemmatizer for the Estonian language, which employs a hybrid approach to handle both in- and out-of-vocabulary words. Our method uses only publicly available data and does not require any external tools such as a POS tagger. In the process of experimentation, we achieved the accuracy of 91%.