Enhancing Active Learning for Semantic Role Labeling via Compressed Dependency Trees

This paper explores new approaches to active learning (AL) for semantic role labeling (SRL), focusing in particular on combining typical informativity-based sampling strategies with a novel measure of representativeness based on compressed dependency trees (CDTs). In essence, the compressed representation encodes the target predicate and the key dependents of the verb complex in the sentence. We first present our method for producing CDTs from the output of an existing dependency parser. The compressed trees are used as features for training a supervised SRL system. Second, we present a study of AL for SRL. We investigate a number of different sample selection strategies, and the best results are achieved by incorporating CDTs for example selection based on both informativity and representativeness. We show that our approach can reduce by up to 50% the amount of training data needed to attain a given level of performance.