Shallow parsing with Hidden Markov Support Vector Machines
Shixi Fan, Lidan Chen, Xuan Wang, Buzhou Tang · 2014
Shallow parsing system, providing natural part syntactic information statement, to meet a lot of language information processing requirements, has received much attention recent years. Hidden Markov Support Vector Machines (HM-SVMs) for sequence labeling offer advantages over both generative models like HMMs and classifying models like SVMs which give labeling result for each positionseparately. We show how to train a HM-SVM model to achieve good performance on the data set of CoNLL2000 share task. The HM-SVMs yields an F-score of 95.51% which is better than any system result of ConLL2000 share task.