Home » Publication » 26168

Dettaglio pubblicazione

2022, Findings of the Association for Computational Linguistics: EMNLP 2022, Pages 4253-4270

Semantic Role Labeling meets definition modeling: Using natural language to describe predicate-argument structures (04b Atto di convegno in volume)

Conia Simone, Barba Edoardo, Scirè Alessandro, Navigli Roberto

One of the common traits of past and present approaches for Semantic Role Labeling (SRL) is that they rely upon discrete labels drawn from a predefined linguistic inventory to classify predicate senses and their arguments.However, we argue this need not be the case. In this paper, we present an approach that leverages Definition Modeling to introduce a generalized formulation of SRL as the task of describing predicate-argument structures using natural language definitions instead of discrete labels. Our novel formulation takes a first step towards placing interpretability and flexibility foremost, and yet our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance. We release our software for research purposes at https://github.com/SapienzaNLP/dsrl.
Gruppo di ricerca: Natural Language Processing
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma