A Novel Method of Citation Sequence Labeling Based on Conditional Random Fields

Citation sequence labeling is an essential phase in citation entity resolution and other applications on citations. Scholars proposed many methods and models. In all the statistical learning models, the conditional random fields (CRFs) is the best one which is studied and used extensively. Most of the papers which study applications based on conditional random fields focus on the three basic questions and pay less attention to feature selection, granularity choosing and structure learning. This paper has discussed the use of text features in citation sequence labeling based on conditional random fields model. According to this, this paper made some differences in structure learning and feature selection. Experimental results show that our algorithm make a further improvement in the precision of citation sequence labeling.