no code implementations • ACL (GEM) 2021 • Lorenzo De Mattei, Huiyuan Lai, Felice Dell’Orletta, Malvina Nissim
We ask subjects whether they perceive as human-produced a bunch of texts, some of which are actually human-written, while others are automatically generated.
no code implementations • SemEval (NAACL) 2022 • Roberto Zamparelli, Shammur Chowdhury, Dominique Brunato, Cristiano Chesi, Felice Dell’Orletta, Md. Arid Hasan, Giulia Venturi
We report the results of the SemEval 2022 Task 3, PreTENS, on evaluation the acceptability of simple sentences containing constructions whose two arguments are presupposed to be or not to be in an ordered taxonomic relation.
1 code implementation • NAACL (CMCL) 2021 • Gabriele Sarti, Dominique Brunato, Felice Dell’Orletta
We then show the effectiveness of linguistic features when explicitly leveraged by a regression model for predicting sentence complexity and compare its results with the ones obtained by a fine-tuned neural language model.
no code implementations • NAACL (CMCL) 2021 • Benedetta Iavarone, Dominique Brunato, Felice Dell’Orletta
We study the influence of context on how humans evaluate the complexity of a sentence in English.
no code implementations • NAACL (DeeLIO) 2021 • Alessio Miaschi, Dominique Brunato, Felice Dell’Orletta, Giulia Venturi
This paper presents an investigation aimed at studying how the linguistic structure of a sentence affects the perplexity of two of the most popular Neural Language Models (NLMs), BERT and GPT-2.
no code implementations • NAACL (DeeLIO) 2021 • Giovanni Puccetti, Alessio Miaschi, Felice Dell’Orletta
Several studies investigated the linguistic information implicitly encoded in Neural Language Models.
no code implementations • COLING 2022 • Federica Merendi, Felice Dell’Orletta, Giulia Venturi
Several studies in the literature on the interpretation of Neural Language Models (NLM) focus on the linguistic generalization abilities of pre-trained models.
1 code implementation • COLING 2022 • Tommaso Caselli, Irene Dini, Felice Dell’Orletta
This paper presents a comprehensive set of probing experiments using a multilingual language model, XLM-R, for temporal relation classification between events in four languages.