Roberto Dessì

Publication Activity (10 Years)

Years Active: 2018-2023
Publications (10 Years): 23

Top Topics

Language Modelling

Agent Communication

Relevance Model

Top Venues

Publications

Mateo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni
Referential Communication in Heterogeneous Communities of Pre-trained Visual Deep Networks. AAMAS (2023)
Saeed Goodarzi, Nikhil Kagita, Dennis Minn, Shufan Wang, Roberto Dessì, Shubham Toshniwal, Adina Williams, Jack Lanchantin, Koustuv Sinha
Robustness of Named-Entity Replacements for In-Context Learning. EMNLP (Findings) (2023)
Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ramakanth Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom
Augmented Language Models: a Survey. CoRR (2023)
Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ramakanth Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom
Augmented Language Models: a Survey. Trans. Mach. Learn. Res. 2023 (2023)
Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, Marco Baroni
Cross-Domain Image Captioning with Discriminative Finetuning. CoRR (2023)
Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, Marco Baroni
Cross-Domain Image Captioning with Discriminative Finetuning. CVPR (2023)
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
Toolformer: Language Models Can Teach Themselves to Use Tools. CoRR (2023)
Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni
Can discrete information extraction prompts generalize across language models? ICLR (2023)
Mateo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni
Referential communication in heterogeneous communities of pre-trained visual deep networks. CoRR (2023)
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
Toolformer: Language Models Can Teach Themselves to Use Tools. NeurIPS (2023)
Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni
Can discrete information extraction prompts generalize across language models? CoRR (2023)
Roberto Dessì, Eleonora Gualdoni, Francesca Franzon, Gemma Boleda, Marco Baroni
Communication breakdown: On the low mutual intelligibility between human and neural captioning. CoRR (2022)
Roberto Dessì, Eleonora Gualdoni, Francesca Franzon, Gemma Boleda, Marco Baroni
Communication breakdown: On the low mutual intelligibility between human and neural captioning. EMNLP (2022)
Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. CoRR (2021)
Roberto Dessì, Eugene Kharitonov, Marco Baroni
Interpretable agent communication from scratch(with a generic visual processor emerging on the side). CoRR (2021)
Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. BlackboxNLP@EMNLP (2021)
Roberto Dessì, Eugene Kharitonov, Marco Baroni
Interpretable agent communication from scratch (with a generic visual processor emerging on the side). NeurIPS (2021)
Mattia Antonino Di Gangi, Matteo Negri, Roldano Cattoni, Roberto Dessì, Marco Turchi
Enhancing Transformer for End-to-end Speech-to-Text Translation. MTSummit (1) (2019)
Roberto Dessì, Marco Baroni
CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks. ACL (1) (2019)
Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game. CoRR (2019)
Roberto Dessì, Marco Baroni
CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks. CoRR (2019)
Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, Marco Turchi
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018. CoRR (2018)
Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, Marco Turchi
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018. IWSLT (2018)