no code implementations • EMNLP 2021 • Mauricio Mazuecos, Franco M. Luque, Jorge Sánchez, Hernán Maina, Thomas Vadora, Luciana Benotti
Visual Dialog is assumed to require the dialog history to generate correct responses during a dialog.
no code implementations • ReInAct 2021 • Mauricio Mazuecos, Patrick Blackburn, Luciana Benotti
Here we present work in progress in the study of the impact of different answering models in human generated questions in GuessWhat?!.
no code implementations • EMNLP (SpLU) 2020 • Alberto Testoni, Claudio Greco, Tobias Bianchi, Mauricio Mazuecos, Agata Marcante, Luciana Benotti, Raffaella Bernardi
By analyzing LXMERT errors and its attention mechanisms, we find that our classification helps to gain a better understanding of the skills required to answer different spatial questions.
no code implementations • Findings (NAACL) 2022 • Jorge Sánchez, Mauricio Mazuecos, Hernán Maina, Luciana Benotti
Referring resolution is the task of identifying the referent of a natural language expression, for example “the woman behind the other woman getting a massage”.
no code implementations • WS 2020 • Mauricio Mazuecos, Alberto Testoni, Raffaella Bernardi, Luciana Benotti
Regarding our first metric, we find that successful dialogues do not have a higher percentage of effective questions for most models.
no code implementations • WS 2020 • Mauricio Mazuecos, Alberto Testoni, Raffaella Bernardi, Luciana Benotti
Task success is the standard metric used to evaluate these systems.