Publications

Selected publications of the language technologies lab

Highlights

Detecting and explaining unfairness in consumer contracts through memory networks
Federico Ruggeri, Francesca Lagioia, Marco Lippi, and Paolo Torroni
Artificial Intelligence and Law 30:59–92, 2022
Attention in Natural Language Processing
Andrea Galassi, Marco Lippi, and Paolo Torroni
IEEE Transactions on Neural Networks and Learning Systems 32(10), pp 4291-4308, 2021
Towards Consumer-Empowering Artificial Intelligence
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
MARGOT: A web server for argumentation mining
Marco Lippi and Paolo Torroni
Expert Systems with Applications, 65:292-303, 2016

Main Peer Reviewed Publications

Leggi dettagli

Preprints and technical reports

Leggi dettagli

Investigating Logic Tensor Networks for Neural-Symbolic Argument Mining
Andrea Galassi, Marco Lippi, Paolo Torroni
October 2021
BANANA: a Benchmark for the Assessment of Neural Architectures for Nucleic Acids
Luca Salvatore Lorello, Andrea Galassi, Paolo Torroni
September 2021
MemBERT: Injecting Unstructured Knowledge into BERT
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.
Tree-constrained Graph Neural Networks for Argument Mining
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.