400 citations · 566 across the 11 of their papers we have counts for
13 papers
OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
Faadil Mustun, Chiara Semenzin, Roberto Dessi +7
Recent advances in bioacoustics have been driven by large-scale corpora and standardized benchmarks, yet existing resources are overwhelmingly bird-centric and shallow per species,…
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
Chiara Semenzin, Faadil Mustun, Roberto Dessi +5
Self-supervised learning (SSL) has opened new opportunities in bioacoustics by enabling scalable modeling of animal vocalizations without the need for expensive manual annotation.…
Cross-Domain Image Captioning with Discriminative Finetuning
Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni +3
Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of va…
Can discrete information extraction prompts generalize across language models?
Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni +2
We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the s…
Augmented Language Models: a Survey
Grégoire Mialon, Roberto Dessì, Maria Lomeli +10
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially comple…
Toolformer: Language Models Can Teach Themselves to Use Tools
Timo Schick, Jane Dwivedi-Yu, Roberto Dessì +5
Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with…
Referential communication in heterogeneous communities of pre-trained visual deep networks
Matéo Mahaut, Francesca Franzon, Roberto Dessì +1
As large pre-trained image-processing neural networks are being embedded in autonomous agents such as self-driving cars or robots, the question arises of how such systems can commu…
Communication breakdown: On the low mutual intelligibility between human and neural captioning
Roberto Dessì, Eleonora Gualdoni, Francesca Franzon +2
We compare the 0-shot performance of a neural caption-based image retriever when given as input either human-produced captions or captions generated by a neural captioner. We condu…
Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN
Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
Despite their practical success, modern seq2seq architectures are unable to generalize systematically on several SCAN tasks. Hence, it is not clear if SCAN-style compositional gene…
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
Roberto Dessì, Eugene Kharitonov, Marco Baroni
As deep networks begin to be deployed as autonomous agents, the issue of how they can communicate with each other becomes important. Here, we train two deep nets from scratch to pe…
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game
Roberto Dessì, Diane Bouchacourt, Davide Crepaldi +1
Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy…
CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks
Roberto Dessì, Marco Baroni
Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of "jump around" 0-…
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni +2
This paper describes FBK's submission to the end-to-end English-German speech translation task at IWSLT 2018. Our system relies on a state-of-the-art model based on LSTMs and CNNs,…