Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

Blloshmi, Rexhina; Conia, Simone; Tripodi, Rocco; Navigli, Roberto

doi:10.24963/ijcai.2021/521

Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling

Rexhina Blloshmi, Simone Conia, Rocco Tripodi, Roberto Navigli

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3786-3793.

https://doi.org/10.24963/ijcai.2021/521

Keywords

Natural Language Processing: Natural Language Semantics
Natural Language Processing: Natural Language Processing
Natural Language Processing: Natural Language Generation

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.

In 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.

Our 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.

Evaluated 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.

Finally, 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.

We release GSRL at github.com/SapienzaNLP/gsrl.

Rexhina Blloshmi, Simone Conia, Rocco Tripodi, and Roberto Navigli. 2021. Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3786–3793. https://doi.org/10.24963/ijcai.2021/521

@inproceedings{ijcai2021p521,
  title     = {Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling},
  author    = {Blloshmi, Rexhina and Conia, Simone and Tripodi, Rocco and Navigli, Roberto},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {3786--3793},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/521},
  url       = {https://doi.org/10.24963/ijcai.2021/521},
}

TY  - CPAPER
TI  - Generating Senses and RoLes: An End-to-End Model for Dependency- and Span-based Semantic Role Labeling
AU  - Blloshmi, Rexhina
AU  - Conia, Simone
AU  - Tripodi, Rocco
AU  - Navigli, Roberto
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3786
EP  - 3793
DO  - 10.24963/ijcai.2021/521
UR  - https://doi.org/10.24963/ijcai.2021/521
ER  -