Semantic Role Labeling Based on Conditional Random Fields
Jiangde Yu, Xiaozhong Fan, Wenbo Pang, Zhengtao Yu · Journal of Southeast University · 2007
Due to the fact that semantic role labeling (SRL) is very necessary for deep natural language processing, a method based on conditional random fields (CRFs) is proposed for the SRL task. This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates' semantic roles in a sentence. The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features: features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected. Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80.43% precision and 63.55% recall for semantic role labeling.