Functional Elements and POS Categories
Qiuye Zhao, Mitch Marcus · International Joint Conference on Natural Language Processing · 2011
We propose a bootstrapping algorithm which successfully resolves two fundamental tasks: morphology acquisition and the acquisition of a subset of functional words. Given the outputs of these fundamental tasks, we build a nearly state-of-art morphology analyzer performing with a F1-score of 80.94%; also, we can improve the baseline model for acquiring functional words by an absolute error reduction of 26%. Furthermore, with these acquisition outputs, a minimally supervised tagging system proposed before can be turned into a totally unsupervised one, achieving a tagging accuracy of 85.26% for openclass words.