1 code implementation • 27 Feb 2024 • Alessio Miaschi, Felice Dell'Orletta, Giulia Venturi
In this paper, we explore the impact of augmenting pre-trained Encoder-Decoder models, specifically T5, with linguistic knowledge for the prediction of a target task.
1 code implementation • 23 May 2022 • Giovanni Puccetti, Anna Rogers, Aleksandr Drozd, Felice Dell'Orletta
While Transformer-based language models are generally very robust to pruning, there is the recently discovered outlier phenomenon: disabling only 48 out of 110M parameters in BERT-base drops its performance by nearly 30% on MNLI.
1 code implementation • ACL (EvalNLGEval, INLG) 2020 • Lorenzo De Mattei, Michele Cafagna, Huiyuan Lai, Felice Dell'Orletta, Malvina Nissim, Albert Gatt
An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based metrics.
no code implementations • COLING 2020 • Alessio Miaschi, Dominique Brunato, Felice Dell'Orletta, Giulia Venturi
In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems.
1 code implementation • 29 Apr 2020 • Lorenzo De Mattei, Michele Cafagna, Felice Dell'Orletta, Malvina Nissim, Marco Guerini
We provide a thorough analysis of GePpeTto's quality by means of both an automatic and a human-based evaluation.