PurePos 2.0: a hybrid tool for morphological disambiguation
György Orosz, Attila Novák · Recent Advances in Natural Language Processing · 2013
We present PurePos, an open-source HMM-based automatic morphological annotation tool. PurePos can perform tagging and lemmatization at the same time, it is very fast to train, with the possibility of easy integration of symbolic rulebased components into the annotation process that can be used to boost the accuracy of the tool. The hybrid approach implemented in PurePos is especially beneficial in the case of rich morphology, highly detailed annotation schemes and if a small amount of training data is available. Evaluation of the tool was on a Hungarian corpus revealed that its hybrid components significantly improve overall annotation accuracy.