Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach

Simone Conia, Roberto Navigli


Abstract
Recent research indicates that taking advantage of complex syntactic features leads to favorable results in Semantic Role Labeling. Nonetheless, an analysis of the latest state-of-the-art multilingual systems reveals the difficulty of bridging the wide gap in performance between high-resource (e.g., English) and low-resource (e.g., German) settings. To overcome this issue, we propose a fully language-agnostic model that does away with morphological and syntactic features to achieve robustness across languages. Our approach outperforms the state of the art in all the languages of the CoNLL-2009 benchmark dataset, especially whenever a scarce amount of training data is available. Our objective is not to reject approaches that rely on syntax, rather to set a strong and consistent language-independent baseline for future innovations in Semantic Role Labeling. We release our model code and checkpoints at https://github.com/SapienzaNLP/multi-srl.
Anthology ID:
2020.coling-main.120
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1396–1410
Language:
URL:
https://aclanthology.org/2020.coling-main.120
DOI:
10.18653/v1/2020.coling-main.120
Bibkey:
Cite (ACL):
Simone Conia and Roberto Navigli. 2020. Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1396–1410, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach (Conia & Navigli, COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.coling-main.120.pdf
Code
 sapienzanlp/multi-srl
Data
CoNLL-2012