Calibrating Features for Semantic Role Labeling

This paper takes a critical look at the features used in the semantic role tagging literature and show that the information in the input, generally a syntactic parse tree, has yet to be fully exploited. We propose an additional set of features and our experiments show that these features lead to fairly significant improvements in the tasks we performed. We further show that different features are needed for different subtasks. Finally, we show that by using a Maximum Entropy classifier and fewer features, we achieved results comparable with the best previously reported results obtained with SVM models. We believe this is a clear indication that developing features that capture the right kind of information is crucial to advancing the stateof-the-art in semantic analysis.

• Type: Conference
• Year: 2004
• Where: EMNLP
• Authors: Nianwen Xue, Martha Palmer
• Keywords: EMNLP 2004, EMNLP 2007, Maximum Entropy Classifier, Role Tagging Literature, Syntactic Parse Tree