Follow
Roberto Dessė
Roberto Dessė
PhD student at FAIR Paris and UPF Barcelona
Verified email at upf.edu - Homepage
Title
Cited by
Cited by
Year
Toolformer: Language models can teach themselves to use tools
T Schick, J Dwivedi-Yu, R Dessė, R Raileanu, M Lomeli, E Hambro, ...
Advances in Neural Information Processing Systems 36, 2024
8702024
Augmented language models: a survey
G Mialon, R Dessė, M Lomeli, C Nalmpantis, R Pasunuru, R Raileanu, ...
arXiv preprint arXiv:2302.07842, 2023
3412023
Enhancing transformer for end-to-end speech-to-text translation
MA Di Gangi, M Negri, R Cattoni, R Dessi, M Turchi
Proceedings of Machine Translation Summit XVII: Research Track, 21-31, 2019
672019
CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks
R Dessė, M Baroni
arXiv preprint arXiv:1905.08527, 2019
522019
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
R Dessė, E Kharitonov, M Baroni
Advances in Neural Information Processing Systems 34, 26937-26949, 2021
282021
Can transformers jump around right in natural language? assessing performance transfer from SCAN
R Chaabouni, R Dessė, E Kharitonov
arXiv preprint arXiv:2107.01366, 2021
192021
Cross-domain image captioning with discriminative finetuning
R Dessė, M Bevilacqua, E Gualdoni, NC Rakotonirina, F Franzon, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
82023
Fine-tuning on clean data for end-to-end speech translation: FBK@ IWSLT 2018
MA Di Gangi, R Dessi, R Cattoni, M Negri, M Turchi
arXiv preprint arXiv:1810.07652, 2018
82018
Time heals all (shallow) wounds: A lesson on forgiveness of ingroup transgressors learned by the Feyenoord Vandal fans
M Rullo, F Presaghi, S Livi, S Mazzuca, R Dessi
Social Sciences 6 (3), 83, 2017
82017
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game
R Dessė, D Bouchacourt, D Crepaldi, M Baroni
arXiv preprint arXiv:1911.01892, 2019
62019
Can discrete information extraction prompts generalize across language models?
NC Rakotonirina, R Dessė, F Petroni, S Riedel, M Baroni
arXiv preprint arXiv:2302.09865, 2023
52023
Communication breakdown: On the low mutual intelligibility between human and neural captioning
R Dessė, E Gualdoni, F Franzon, G Boleda, M Baroni
arXiv preprint arXiv:2210.11512, 2022
52022
Emergent language-based coordination in deep multi-agent systems
M Baroni, R Dessė, A Lazaridou
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
32022
Referential communication in heterogeneous communities of pre-trained visual deep networks
M Mahaut, F Franzon, R Dessė, M Baroni
arXiv preprint arXiv:2302.08913, 2023
22023
Robustness of Named-Entity Replacements for In-Context Learning
S Goodarzi, N Kagita, D Minn, S Wang, R Dessė, S Toshniwal, A Williams, ...
Findings of the Association for Computational Linguistics: EMNLP 2023, 10914 …, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–15