{"type":"ScholarlyArticle","title":"Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling","authors":[{"name":"Rexhina Blloshmi","slug":"rexhina-blloshmi","given":"Rexhina","family":"Blloshmi","affiliation":""},{"name":"Simone Conia","slug":"simone-conia","given":"Simone","family":"Conia","affiliation":""},{"name":"Rocco Tripodi","slug":"rocco-tripodi","given":"Rocco","family":"Tripodi","affiliation":""},{"name":"Roberto Navigli","slug":"roberto-navigli","given":"Roberto","family":"Navigli","affiliation":""}],"abstract":"Despite the recent great success of the sequence-to-sequence paradigm in Natural Language Processing, the majority of current studies in Semantic Role Labeling (SRL) still frame the problem as a sequence labeling task.\r\nIn this paper we go against the flow and propose GSRL (Generating Senses and RoLes), the first sequence-to-sequence model for end-to-end SRL.\r\nOur approach benefits from recently-proposed decoder-side pretraining techniques to generate both sense and role labels for all the predicates in an input sentence at once, in an end-to-end fashion.\r\nEvaluated on standard gold benchmarks, GSRL achieves state-of-the-art results in both dependency- and span-based English SRL, proving empirically that our simple generation-based model can learn to produce complex predicate-argument structures.\r\nFinally, we propose a framework for evaluating the robustness of an SRL model in a variety of synthetic low-resource scenarios which can aid human annotators in the creation of better, more diverse, and more challenging gold datasets.\r\nWe release GSRL at github.com/SapienzaNLP/gsrl.","doi":"10.24963/ijcai.2021/521","url":"https://ijcai.org/proceedings/2021/521","pdf":"https://ijcai.org/proceedings/2021/0521.pdf","markdown":"https://ijcai.org/proceedings/2021/521.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/521","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Natural Language Processing","track":"Main Track","number":521,"pages":{"first":3786,"last":3793},"keywords":["Natural Language Processing: Natural Language Semantics","Natural Language Processing: Natural Language Processing","Natural Language Processing: Natural Language Generation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}