Alberto Testoni
Cited by
Cited by
Grounded textual entailment
HT Vu, C Greco, A Erofeeva, S Jafaritazehjan, G Linders, M Tanti, ...
arXiv preprint arXiv:1806.05645, 2018
They are not all alike: Answering different spatial questions requires different grounding strategies
A Testoni, C Greco, T Bianchi, M Mazuecos, A Marcante, L Benotti, ...
Proceedings of the Third International Workshop on Spatial Language …, 2020
A software architecture for generic human activity recognition from smartphone sensor data
A Testoni, M Di Felice
2017 IEEE International Workshop on Measurement and Networking (M&N), 1-6, 2017
Looking for confirmations: An effective and human-like visual dialogue strategy
A Testoni, R Bernardi
arXiv preprint arXiv:2109.05312, 2021
The interplay of task success and dialogue quality: An in-depth evaluation in task-oriented visual dialogues
A Testoni, R Bernardi
arXiv preprint arXiv:2103.11151, 2021
Artificial intelligence models do not ground negation, humans do. guesswhat?! dialogues as a case study
A Testoni, C Greco, R Bernardi
Frontiers in big Data 4, 736709, 2022
Grounding dialogue history: Strengths and weaknesses of pre-trained transformers
C Greco, A Testoni, R Bernardi
International Conference of the Italian Association for Artificial …, 2020
On the role of effective and referring questions in GuessWhat?!
M Mazuecos, A Testoni, R Bernardi, L Benotti
Proceedings of the first workshop on advances in language and vision …, 2020
Quantifiers in a multimodal world: Hallucinating vision with language and sound
A Testoni, S Pezzelle, R Bernardi
Proceedings of the workshop on cognitive modeling and computational …, 2019
The devil is in the detail: A magnifying glass for the GuessWhich visual dialogue game
A Testoni, R Shekhar, R Fernández, R Bernardi
Proceedings of the 23rd SemDial workshop on the semantics and pragmatics of …, 2019
Jointly Learning to See, Ask, Decide when to Stop, and then GuessWhat.
R Shekhar, A Testoni, R Fernández, R Bernardi
CLiC-it, 2019
“I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?!
A Testoni, R Bernardi
Proceedings of the 59th Annual Meeting of the Association for Computational …, 2021
A Small but Informed and Diverse Model: The Case of the Multimodal GuessWhat!? Guessing Game
C Greco, A Testoni, R Bernardi, S Frank
Proceedings of the 2022 CLASP Conference on (Dis) embodiment, 1-10, 2022
ACT-thor: A controlled benchmark for embodied action understanding in simulated environments
M Hanna, F Pedeni, A Testoni, A Suglia, R Bernardi
Proceedings of the 29th International Conference on Computational …, 2022
Visually grounded follow-up questions: A dataset of spatial questions which require dialogue history
T Dong, A Testoni, L Benotti, R Bernardi
Proceedings of Second International Combined Workshop on Spatial Language …, 2021
Overprotective training environments fall short at testing time: Let models contribute to their own training
A Testoni, R Bernardi
arXiv preprint arXiv:2103.11145, 2021
Yes” and “No”: Visually grounded polar answers
C Greco, A Testoni, R Bernardi
Proceedings of visually grounded interaction and language (ViGIL), 2021
Which Turn do Neural Models Exploit the Most to Solve GuessWhat? Diving into the Dialogue History Encoding in Transformers and LSTMs.
C Greco, A Testoni, R Bernardi
NL4AI@ AI* IA, 29-43, 2020
Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions
A Testoni, R Fernández
arXiv preprint arXiv:2402.06509, 2024
Asking Strategic and Informative Questions in Visual Dialogue Games: Strengths and Weaknesses of Neural Generative Models
A Testoni
Università degli studi di Trento, 2023
The system can't perform the operation now. Try again later.
Articles 1–20