Search Results for author: Felice Dell'Orletta

Found 4 papers, 2 papers with code

Outliers Dimensions that Disrupt Transformers Are Driven by Frequency

no code implementations23 May 2022 Giovanni Puccetti, Anna Rogers, Aleksandr Drozd, Felice Dell'Orletta

We also find that, surprisingly, the outlier effect on the model performance varies by layer, and that variance is also related to the correlation between outlier magnitude and encoded token frequency.

On the interaction of automatic evaluation and task framing in headline style transfer

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.

Style Transfer

Linguistic Profiling of a Neural Language Model

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.

Language Modelling

GePpeTto Carves Italian into a Language Model

1 code implementation29 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.

Language Modelling Sentence Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.