Piecewise Large Margin Learning for Partially Annotated Sequences

Xiaolei Lu, Tommy W. S. Chow, Haijun Zhang

Abstract: Supervised and semi-supervised sequence labeling methods require large amounts of fully annotated training sequences or exact annotations of structured outputs. The problem of learning from partially annotated sequences arises in many applications, for example, Natural Language Processing and Computational Biology. In this paper, we propose Piecewise Convex Learning from Partial Labels (PW-CLPL) which is an effective discriminative structured learning method for sequence labeling as global training is intractable for partially annotated sequences. A small number of constraints is reformulated for the optimization, which improve the efficiency of parameters learning. Experimental results on the reconstructed dataset CoNLL-2000 show the effectiveness of the proposed model in the setting of partial annotations.