Goodarzi, S. and Kagita, N. and Minn, D. and Wang, S. and Dessì, R. and Toshniwal, S. and Williams, A. and Lanchantin, J. and Koustuv Sinha
Cross-Domain Image Captioning with Discriminative Finetuning
EMNLP 2023 (Findings), Singapore
Dessì, R. and Bevilacqua, M. and Gualdoni, E. and Rakotonirina, N.C. and Franzon, F. and Baroni M.
Cross-Domain Image Captioning with Discriminative Finetuning
CVPR 2023, Vancouver
Schick, T. and Dwivedi-Yu, J. and Dessì, R. and Raileanu, R. and Lomeli, M. and Zettlemoyer, L. and Cancedda, N. and Scialom T.
Toolformer: Language Models Can Teach Themselves to Use Tools
NeurIPS 2023, New Orleans
Mialon, G., and Dessì, R. and Lomeli, M., and Nalmpantis, C. and Pasunuru, R., and Raileanu, R. and Rozière, R. and Schick, T. and Dwivedi-Yu, J., and Celikyilmaz, A. and Grave, E., and LeCun, Y. and Scialom T.
Augmented Language Models: a Survey
TMLR
Rakotonirina, N.C. and Dessì, R. and Petroni F., and Riedel, S. and Baroni M.
Can discrete information extraction prompts generalize across language models?
ICLR 2023, Kigali
Dessì, R. and Gualdoni, E. and Franzon, F. and Boleda, G. and Baroni M.
Communication breakdown: On the low mutual intelligibility between human and neural captioning
EMNLP 2022, Abu Dhabi
Dessì, R. and Kharitonov, E. and Baroni M.
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
NeurIPS 2020, Virtual
Dessì, R. and Bouchacourt, D. and Crepaldi, D. and Baroni M.
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game
2019 Workshop on Emergent Commuincation at NeurIPS, Vancouver
Dessi, R. and Baroni M.
CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks
ACL 2019, Florence
Di Gangi, M.A. and Negri, M. and Cattoni, R. and Dessì, R. and Turchi M.
Enhancing transformer for end-to-end speech-to-text translation
MT Summit 2019, Dublin
Di Gangi, M.A. and Dessì, R. and Cattoni, R. and Negri, M. and Turchi M.
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
IWSLT 2018, Bruges