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.

Bridging the Gap in Multilingual Semantic Role Labeling: A Language-Agnostic Approach / Conia, Simone; Navigli, Roberto. - (2020), pp. 1396-1410. (Intervento presentato al convegno 28th International Conference on Computational Linguistics, COLING 2020 tenutosi a Online) [10.18653/v1/2020.coling-main.120].

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

Conia, Simone
Primo
;
Navigli, Roberto
Ultimo
2020

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.
2020
28th International Conference on Computational Linguistics, COLING 2020
natural language processing; semantic role labeling; multilinguality; deep learning; artificial intelligence;
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Bridging the Gap in Multilingual Semantic Role Labeling: A Language-Agnostic Approach / Conia, Simone; Navigli, Roberto. - (2020), pp. 1396-1410. (Intervento presentato al convegno 28th International Conference on Computational Linguistics, COLING 2020 tenutosi a Online) [10.18653/v1/2020.coling-main.120].
File allegati a questo prodotto
File Dimensione Formato  
Conia_Bridging_2020.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 699.29 kB
Formato Adobe PDF
699.29 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1494224
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? ND
social impact