1 code implementation • ArgMining (ACL) 2022 • Eleonora Mancini, Federico Ruggeri, Andrea Galassi, Paolo Torroni
We propose a study on multimodal argument mining in the domain of political debates.
1 code implementation • ArgMining (ACL) 2022 • Giulia Grundler, Piera Santin, Andrea Galassi, Federico Galli, Francesco Godano, Francesca Lagioia, Elena Palmieri, Federico Ruggeri, Giovanni Sartor, Paolo Torroni
The successful application of argument mining in the legal domain can dramatically impact many disciplines related to law.
no code implementations • EMNLP (NLLP) 2021 • Kasper Drawzeski, Andrea Galassi, Agnieszka Jablonowska, Francesca Lagioia, Marco Lippi, Hans Wolfgang Micklitz, Giovanni Sartor, Giacomo Tagiuri, Paolo Torroni
We present the first annotated corpus for multilingual analysis of potentially unfair clauses in online Terms of Service.
1 code implementation • 26 Mar 2024 • Davide Baldelli, Junfeng Jiang, Akiko Aizawa, Paolo Torroni
In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM).
1 code implementation • 15 Feb 2024 • Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo Torroni
Real-world business applications require a trade-off between language model performance and size.
no code implementations • 29 Sep 2021 • Luca Salvatore Lorello, Andrea Galassi, Paolo Torroni
Machine learning has always played an important role in bioinformatics and recent applications of deep learning have allowed solving a new spectrum of biologically relevant tasks.
1 code implementation • 2 Sep 2021 • Federico Ruggeri, Marco Lippi, Paolo Torroni
By imposing a series of regularization constraints to the learning problem, we exploit a pooling mechanism that incorporates such notion of fragments within the node soft assignment function that produces the embeddings.
1 code implementation • 2 Sep 2021 • Federico Ruggeri, Marco Lippi, Paolo Torroni
Many NLP applications require models to be interpretable.
no code implementations • 26 Jul 2021 • Bettina Fazzinga, Andrea Galassi, Paolo Torroni
Dialogue systems are widely used in AI to support timely and interactive communication with users.
1 code implementation • 24 Feb 2021 • Andrea Galassi, Marco Lippi, Paolo Torroni
We explore the use of residual networks and neural attention for multiple argument mining tasks.
Ranked #1 on Link Prediction on AbstRCT - Neoplasm
1 code implementation • COLING 2020 • Andrea Galassi, Kasper Drazewski, Marco Lippi, Paolo Torroni
We study annotation projection in text classification problems where source documents are published in multiple languages and may not be an exact translation of one another.
no code implementations • 24 Jul 2020 • Federico Ruggeri, Francesca Lagioia, Marco Lippi, Paolo Torroni
Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents.
no code implementations • 28 May 2020 • 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 data, and to efficiently retrieve results.
no code implementations • 22 May 2019 • Andrea Galassi, Kristian Kersting, Marco Lippi, Xiaoting Shao, Paolo Torroni
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 tasks.
no code implementations • 4 Feb 2019 • Andrea Galassi, Marco Lippi, Paolo Torroni
Attention is an increasingly popular mechanism used in a wide range of neural architectures.
1 code implementation • WS 2018 • Andrea Galassi, Marco Lippi, Paolo Torroni
We explore the use of residual networks for argumentation mining, with an emphasis on link prediction.
1 code implementation • 3 May 2018 • Marco Lippi, Przemyslaw Palka, Giuseppe Contissa, Francesca Lagioia, Hans-Wolfgang Micklitz, Giovanni Sartor, Paolo Torroni
Terms of service of on-line platforms too often contain clauses that are potentially unfair to the consumer.