no code implementations • EMNLP (ACL) 2021 • Riccardo Orlando, Simone Conia, Fabrizio Brignone, Francesco Cecconi, Roberto Navigli
Over the past few years, Word Sense Disambiguation (WSD) has received renewed interest: recently proposed systems have shown the remarkable effectiveness of deep learning techniques in this task, especially when aided by modern pretrained language models.
no code implementations • EMNLP (ACL) 2021 • Simone Conia, Riccardo Orlando, Fabrizio Brignone, Francesco Cecconi, Roberto Navigli
Notwithstanding the growing interest in cross-lingual techniques for Natural Language Processing, there has been a surprisingly small number of efforts aimed at the development of easy-to-use tools for cross-lingual Semantic Role Labeling.
no code implementations • EMNLP 2020 • Simone Conia, Fabrizio Brignone, Davide Zanfardino, Roberto Navigli
Semantic Role Labeling (SRL) is deeply dependent on complex linguistic resources and sophisticated neural models, which makes the task difficult to approach for non-experts.
no code implementations • ACL 2020 • Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi, Roberto Navigli
Exploiting syntagmatic information is an encouraging research focus to be pursued in an effort to close the gap between knowledge-based and supervised Word Sense Disambiguation (WSD) performance.