Prediction of Maximal Projection for Semantic Role Labeling

摘要

In Semantic Role Labeling (SRL), arguments are usually limited in a syntax subtree. It is reasonable to label arguments locally in such a sub-tree rather than a whole tree. To identify active region of arguments, this paper models Maximal Projection (MP), which is a concept in D-structure from the projection principle of the Principle and Parameters theory. This paper makes a new definition of MP in S-structure and proposes two methods to predict it: the anchor group approach and the single anchor approach. The anchor group approach achieves an accuracy of 87.75% and the single anchor approach achieves 83.63%. Experimental results also indicate that the prediction of MP improves semantic role labeling.