In this paper, we propose a new approach to construct a system oftransformation rules for the Part-of-Speech (POS) tagging task. Our approach isbased on an incremental knowledge acquisition method where rules are stored inan exception structure and new rules are only added to correct the errors ofexisting rules; thus allowing systematic control of the interaction between therules. Experimental results on 13 languages show that our approach is fast interms of training time and tagging speed. Furthermore, our approach obtainsvery competitive accuracy in comparison to state-of-the-art POS andmorphological taggers.
展开▼
