Towards Open-Domain Semantic Role Labeling

Current Semantic Role Labeling technologies are based on inductive algorithms trained over large scale repositories of annotated examples. Frame-based systems currently make use of the FrameNet database but fail to show suitable generalization capabilities in out-of-domain scenarios. In this paper, a state-of-art system for frame-based SRL is extended through the encapsulation of a distributional model of semantic similarity. The resulting argument classification model promotes a simpler feature space that limits the potential overfitting effects. The large scale empirical study here discussed confirms that state-of-art accuracy can be obtained for out-of-domain evaluations.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Danilo Croce, Cristina Giannone, Paolo Annesi, Roberto Basili
• Keywords: ACL 2010, Computational Linguistics, Large Scale, Large Scale Repositories, Semantic Role Labeling