Paper: Robustness and Generalization of Role Sets: PropBank vs. VerbNet

ACL ID P08-1063
Title Robustness and Generalization of Role Sets: PropBank vs. VerbNet
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

This paper presents an empirical study on the robustness and generalization of two alterna- tive role sets for semantic role labeling: Prop- Bank numbered roles and VerbNet thematic roles. By testing a state–of–the–art SRL sys- tem with the two alternative role annotations, we show that the PropBank role set is more robust to the lack of verb–specific semantic information and generalizes better to infre- quent and unseen predicates. Keeping in mind that thematic roles are better for application needs, we also tested the best way to generate VerbNet annotation. We conclude that tagging first PropBank roles and mapping into Verb- Net roles is as effective as training and tagging directly on VerbNet, and more robust for do- main shifts.