no code implementations • NAACL (SIGTYP) 2022 • Andrea De Varda, Roberto Zamparelli
We showed that while both models were favoured by a Zipfian distribution of the tokens and by the presence of head-dependency type structures, the multilingual transformer network exhibited a stronger reliance on hierarchical cues compared to its monolingual counterpart.
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.
no code implementations • games (LREC) 2022 • Natallia Chaiko, Sia Sepanta, Roberto Zamparelli
We discuss the need, the core mechanism and the challenges ahead.
1 code implementation • WS 2019 • Shammur Absar Chowdhury, Roberto Zamparelli
We propose a novel approach to the study of how artificial neural network perceive the distinction between grammatical and ungrammatical sentences, a crucial task in the growing field of synthetic linguistics.
1 code implementation • COLING 2018 • Shammur Absar Chowdhury, Roberto Zamparelli
The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra arguments and subject-relative clause island violations), and considers its implications for the debate on language innatism.
no code implementations • SEMEVAL 2014 • Marco Marelli, Luisa Bentivogli, Marco Baroni, Raffaella Bernardi, Stefano Menini, Roberto Zamparelli
no code implementations • LREC 2014 • Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, Roberto Zamparelli
Shared and internationally recognized benchmarks are fundamental for the development of any computational system.