Selected publications of the language technologies lab
Federico Ruggeri, Mohsen Mesgar, Iryna Gurevych
61st Annual Meeting of the Association for Computational Linguistics (ACL), pp. 7684–7699, 2023
Andrea Galassi, Marco Lippi, Paolo Torroni
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:1877-1892, 2023
Santin, Piera; Grundler, Giulia; Galassi, Andrea; Galli, Federico; Lagioia, Francesca; Palmieri, Elena; Ruggeri, Federico; Sartor, Giovanni; Torroni, Paolo
19th International Conference on Artificial Intelligence and Law (ICAIL), pp. 247–256, 2023
Alberto Barrón-Cedeño, Firoj Alam, Tommaso Caselli, Giovanni Da San Martino, Tamer Elsayed, Andrea Galassi, Fatima Haouari, Federico Ruggeri, Julia Maria Struß, Rabindra Nath Nandi, Gullal S. Cheema, Dilshod Azizov, Preslav Nakov
European Conference on Information Retrieval (ECIR), pp. 506-517, 2023
Federico Galli, Giulia Grundler, Alessia Fidangeli, Andrea Galassi, Francesca Lagioia, Federico Ruggeri, Giovanni Sartor, Paolo Torroni
35th International Conference on Legal Knowledge and Information Systems (JURIX), pp. 188 - 193, 2022
Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo Torroni
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP): Industry Track, 2022
Bettina Fazzinga, Andrea Galassi, PaoloTorroni
Intelligent Systems with Applications 16:200113, 2022
Marco Lippi, Francesco Antici, Gianfranco Brambilla, Evaristo Cisbani, Andrea Galassi, Daniele Giansanti, Fabio Magurano, Antonella Rosi, Federico Ruggeri, Paolo Torroni
31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI), Demonstration Track, pp. 5932-5935, 2022
Gianfranco Brambilla, Antonella Rosi, Francesco Antici, Andrea Galassi, Daniele Giansanti, Fabio Magurano, Federico Ruggeri, Paolo Torroni, Evaristo Cisbani, Marco Lippi
Frontiers in Public Health 10:945181, 2022
Federico Ruggeri, Francesca Lagioia, Marco Lippi, and Paolo Torroni
Artificial Intelligence and Law 30:59–92, 2022
Bettina Fazzinga, Andrea Galassi, Paolo Torroni
4th International Conference on Logic and Argumentation (CLAR), pp. 477–485, 2021
Francesco Antici, Luca Bolognini, Marco Antonio Inajetovic, Bogdan Ivasiuk, Andrea Galassi, Federico Ruggeri
12th Conference and Labs of the Evaluation Forum (CLEF), pp. 40–52, 2021
Andrea Galassi, Marco Lippi, and Paolo Torroni
IEEE Transactions on Neural Networks and Learning Systems 32(10), pp 4291-4308, 2021 (first online 2020)
Andrea Galassi, Kasper Drazewski, Marco Lippi, Paolo Torroni
28th International Conference on Computational Linguistics (COLING), pp. 915 - 926, 2020
Andrea Galassi, Kristian Kersting, Marco Lippi, Xiaoting Shao, and Paolo Torroni
Frontiers in Big Data, 2:1-6, 2020
Marco Lippi, Giuseppe Contissa, Agnieszka Jablonowska, Francesca Lagioia, Hans-Wolfgang Micklitz, Przemyslaw Palka, Giovanni Sartor, and Paolo Torroni
Journal of Artificial Intelligence Research, 67, 2020
Marco Lippi, Przemysław Pałka, Giuseppe Contissa, Francesca Lagioia, Hans-Wolfgang Micklitz, Giovanni Sartor, and Paolo Torroni
Artificial Intelligence and Law, 27:117–139, 2019
Marco Lippi, Giuseppe Contissa, Francesca Lagioia, Hans-Wolfgang Micklitz, Przemysław Pałka, Giovanni Sartor, and Paolo Torroni
Nature Machine Intelligence 1:168–169, 2019
Francesca Lagioia, Federico Ruggeri, Kasper Drazewski, Marco Lippi, Hans-Wolfgang Micklitz, Paolo Torroni, and Giovanni Sartor.
32nd Annual Conference on Legal Knowledge and Information Systems (JURIX), pp. 43-52, 2019
Tobias Mayer, Elena Cabrio, Marco Lippi, Paolo Torroni, and Serena Villata
7th International Conference on Computational Models of Argument (COMMA), pp. 137-148, 2018
Giuseppe Contissa, Francesca Lagioia, Marco Lippi, Hans-Wolfgang Micklitz, Przemyslaw Palka, Giovanni Sartor, and Paolo Torroni
27th International Joint Conference on Artificial Intelligence (IJCAI), pp. 5150–5157, 2018
Giuseppe Contissa, Koen Docter, Francesca Lagioia, Marco Lippi, Hans-Wolfgang Micklitz, Przemyslaw Palka, Giovanni Sartor, and Paolo Torroni
31st Annual Conference on Legal Knowledge and Information Systems (JURIX), pp. 51-60, 2018
Marco Lippi, Francesca Lagioia, Giuseppe Contissa, Giovanni Sartor, and Paolo Torroni
AI Approaches to the Complexity of Legal Systems (AICOL), pp. 513-527, 2018
Marco Lippi, Przemyslaw Palka, Giuseppe Contissa, Francesca Lagioia, Hans-Wolfgang Micklitz, Yannis Panagis, Giovanni Sartor, and Paolo Torroni
30th Annual Conference on Legal Knowledge and Information Systems (JURIX), pp. 145-154, 2017
Marco Lippi and Paolo Torroni
Expert Systems with Applications, 65:292-303, 2016
Marco Lippi and Paolo Torroni
ACM Transactions on Internet Technology, 2016
Marco Lippi and Paolo Torroni
30th AAAI Conference on Artificial Intelligence (AAAI), pp. 2979-2985, 2016
Zeynep Kiziltan, Marco Lippi, and Paolo Torroni
25th International Joint Conference on Artificial Intelligence (IJCAI), pp. 744-750, 2016
Marco Lippi and Paolo Torroni
24th International Joint Conference on Artificial Intelligence (IJCAI), pp. 185-191, 2015
Marco Lippi and Paolo Torroni
3rd International Workshop on Theory and Applications of Formal Argumentation (TAFA), pp. 163-176, 2015
Joel Niklaus, Veton Matoshi, Pooja Rani, Andrea Galassi, Matthias Stürmer, Ilias Chalkidis
January 2023
Andrea Galassi, Marco Lippi, Paolo Torroni
October 2021
Luca Salvatore Lorello, Andrea Galassi, Paolo Torroni
September 2021
Transformers changed modern NLP in many ways. However, they can hardly exploit domain knowledge, and like other blackbox models, they lack interpretability. Unfortunately, structured knowledge injection, in the long run, risks to suffer from a knowledge acquisition bottleneck. We thus propose a memory enhancement of transformer models that makes use of unstructured domain knowledge expressed in plain natural language. An experimental evaluation conducted on two challenging NLP tasks demonstrates that our approach yields better performance and model interpretability than baseline transformer-based architectures.
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 substructures, named fragments. 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. We present an extensive experimental evaluation on a collection of sentence classification tasks conducted on several argument mining corpora, showing that the proposed approach performs well with respect to state-of-the-art techniques.