15 citations · 50 across the 14 of their papers we have counts for
15 papers
MSTS: A Multimodal Safety Test Suite for Vision-Language Models
Paul Röttger, Giuseppe Attanasio, Felix Friedrich +19
Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards,…
Are Compressed Language Models Less Subgroup Robust?
Leonidas Gee, Andrea Zugarini, Novi Quadrianto
To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models. However, little is known about their robustness to…
Neural paraphrasing by automatically crawled and aligned sentence pairs
Achille Globo, Antonio Trevisi, Andrea Zugarini +3
Paraphrasing is the task of re-writing an input text using other words, without altering the meaning of the original content. Conversational systems can exploit automatic paraphras…
Fast Vocabulary Transfer for Language Model Compression
Leonidas Gee, Andrea Zugarini, Leonardo Rigutini +1
Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer.…
BUSTER: a "BUSiness Transaction Entity Recognition" dataset
Andrea Zugarini, Andrew Zamai, Marco Ernandes +1
Albeit Natural Language Processing has seen major breakthroughs in the last few years, transferring such advances into real-world business cases can be challenging. One of the reas…
Multi-word Tokenization for Sequence Compression
Leonidas Gee, Leonardo Rigutini, Marco Ernandes +1
Large Language Models have proven highly successful at modelling a variety of tasks. However, this comes at a steep computational cost that hinders wider industrial uptake. In this…
The WebCrow French Crossword Solver
Giovanni Angelini, Marco Ernandes, Tommaso laquinta +5
Crossword puzzles are one of the most popular word games, played in different languages all across the world, where riddle style can vary significantly from one country to another.…
An energy-based comparative analysis of common approaches to text classification in the Legal domain
Sinan Gultekin, Achille Globo, Andrea Zugarini +2
Most Machine Learning research evaluates the best solutions in terms of performance. However, in the race for the best performing model, many important aspects are often overlooked…
Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors
Dario Zanca, Andrea Zugarini, Simon Dietz +4
Understanding the mechanisms underlying human attention is a fundamental challenge for both vision science and artificial intelligence. While numerous computational models of free-…
Generate and Revise: Reinforcement Learning in Neural Poetry
Andrea Zugarini, Luca Pasqualini, Stefano Melacci +1
Writers, poets, singers usually do not create their compositions in just one breath. Text is revisited, adjusted, modified, rephrased, even multiple times, in order to better conve…
Vulgaris: Analysis of a Corpus for Middle-Age Varieties of Italian Language
Andrea Zugarini, Matteo Tiezzi, Marco Maggini
Italian is a Romance language that has its roots in Vulgar Latin. The birth of the modern Italian started in Tuscany around the 14th century, and it is mainly attributed to the wor…
An Optimal Control Approach to Learning in SIDARTHE Epidemic model
Andrea Zugarini, Enrico Meloni, Alessandro Betti +3
The COVID-19 outbreak has stimulated the interest in the proposal of novel epidemiological models to predict the course of the epidemic so as to help planning effective control str…
Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances
Marco Maggini, Giuseppe Marra, Stefano Melacci +1
We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that…
An Unsupervised Character-Aware Neural Approach to Word and Context Representation Learning
Giuseppe Marra, Andrea Zugarini, Stefano Melacci +1
In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, a…
Neural Networks for Beginners. A fast implementation in Matlab, Torch, TensorFlow
Francesco Giannini, Vincenzo Laveglia, Alessandro Rossi +2
This report provides an introduction to some Machine Learning tools within the most common development environments. It mainly focuses on practical problems, skipping any theoretic…