645 citations · 876 across the 11 of their papers we have counts for
11 papers
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.…
Combining Transformers with Natural Language Explanations
Federico Ruggeri, Marco Lippi, Paolo Torroni
Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A poss…
Tree-Constrained Graph Neural Networks For Argument Mining
Federico Ruggeri, Marco Lippi, Paolo Torroni
We propose a novel architecture for Graph Neural Networks that is inspired by the idea behind Tree Kernels of measuring similarity between trees by taking into account their common…
An Argumentative Dialogue System for COVID-19 Vaccine Information
Bettina Fazzinga, Andrea Galassi, Paolo Torroni
Dialogue systems are widely used in AI to support timely and interactive communication with users. We propose a general-purpose dialogue system architecture that leverages computat…
Multi-Task Attentive Residual Networks for Argument Mining
Andrea Galassi, Marco Lippi, Paolo Torroni
We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, an…
Memory networks for consumer protection:unfairness exposed
Federico Ruggeri, Francesca Lagioia, Marco Lippi +1
Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents. However, a shortcoming of data-dri…
Parallelizing Machine Learning as a Service for the End-User
Daniela Loreti, Marco Lippi, Paolo Torroni
As ML applications are becoming ever more pervasive, fully-trained systems are made increasingly available to a wide public, allowing end-users to submit queries with their own dat…
Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning
Andrea Galassi, Kristian Kersting, Marco Lippi +2
Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap toward performing advanced reasoning…
Attention in Natural Language Processing
Andrea Galassi, Marco Lippi, Paolo Torroni
Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the…
Blocking time under basic priority inheritance: Polynomial bound and exact computation
Paolo Torroni, Zeynep Kiziltan, Eugenio Faldella
The Priority Inheritance Protocol (PIP) is arguably the best-known protocol for resource sharing under real-time constraints. Its importance in modern applications is undisputed. N…
CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service
Marco Lippi, Przemyslaw Palka, Giuseppe Contissa +4
Terms of service of on-line platforms too often contain clauses that are potentially unfair to the consumer. We present an experimental study where machine learning is employed to…