Abstract
Despite the significant advances made in Semantic Role Labeling (SRL), much work in this field has been carried out with a focus on verbal predicates, with the research on nominal SRL lagging behind. In many contexts, however, nominal predicates are often as informative as verbal ones, thus calling for proper treatment. In this paper we aim to fill this gap and make nominal SRL a first-class citizen. We introduce a novel approach in order to create the first large-scale, high-quality inventory of nominal predicates and organize them into semanticallycoherent frames. Although it is automatically created, NounAtlas – our nominal frame inventory – is subsequently fully validated. We then put forward a technique for generating silver training data for nominal SRL and show that a state-of-the-art SRL model can achieve good performance. Interestingly, thanks to our design choices, which enable seamless integration of our predicate inventory with its verbal counterpart, i.e., VerbAtlas, we can mix verbal and nominal data and perform robust SRL on both types of predicate.
- Outstanding Paper Award ACL 2024
- Roberto Navigli, Pasquale Silvestri, Marco Lo Pinto, Dennis Rotondi, Simone Ciciliano, Alessandro Scirè. 2024. NounAtlas: Filling the Gap in Nominal Semantic Role Labeling. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16245–16258, Bangkok, Thailand. Association for Computational Linguistics.