Zobrazeno 1 - 10
of 1 045
pro vyhledávání: '"Torroni P."'
Speech impairments in Parkinson's disease (PD) provide significant early indicators for diagnosis. While models for speech-based PD detection have shown strong performance, their interpretability remains underexplored. This study systematically evalu
Externí odkaz:
http://arxiv.org/abs/2411.08013
Autor:
Fazzinga, Bettina, Palmieri, Elena, Vestoso, Margherita, Bolognini, Luca, Galassi, Andrea, Furfaro, Filippo, Torroni, Paolo
We present ACME: A Chatbot for asylum-seeking Migrants in Europe. ACME relies on computational argumentation and aims to help migrants identify the highest level of protection they can apply for. This would contribute to a more sustainable migration
Externí odkaz:
http://arxiv.org/abs/2407.09197
Large language models present opportunities for innovative Question Answering over Knowledge Graphs (KGQA). However, they are not inherently designed for query generation. To bridge this gap, solutions have been proposed that rely on fine-tuning or a
Externí odkaz:
http://arxiv.org/abs/2407.01409
Autor:
Ruggeri, Federico, Misino, Eleonora, Muti, Arianna, Korre, Katerina, Torroni, Paolo, Barrón-Cedeño, Alberto
We introduce the Guideline-Centered annotation process, a novel data annotation methodology focused on reporting the annotation guidelines associated with each data sample. We identify three main limitations of the standard prescriptive annotation pr
Externí odkaz:
http://arxiv.org/abs/2406.14099
Autor:
Mancini, Eleonora, Tanevska, Ana, Galassi, Andrea, Galatolo, Alessio, Ruggeri, Federico, Torroni, Paolo
Current research in machine learning and artificial intelligence is largely centered on modeling and performance evaluation, less so on data collection. However, recent research demonstrated that limitations and biases in data may negatively impact t
Externí odkaz:
http://arxiv.org/abs/2406.04116
In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM). TWOLAR introduces a new scoring strategy and a distillation process consisting in the creation of a
Externí odkaz:
http://arxiv.org/abs/2403.17759
Publikováno v:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022): Industry Track
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. We evaluate the method on various vertical domains and downstream task
Externí odkaz:
http://arxiv.org/abs/2402.09977
Publikováno v:
Toxicology Reports, Vol 13, Iss , Pp 101683- (2024)
Introduction: Intentional multiple drugs overdose is an often-encountered method of self-harm in adolescence. Treatments include supportive therapy, antidotes (when available) and decontamination techniques with the aim of reducing drugs absorption b
Externí odkaz:
https://doaj.org/article/4c44673ebae945139256fd344d687194
Publikováno v:
Frontiers in Marine Science, Vol 11 (2024)
The Mediterranean Sea is a biodiversity hotspot, being home to a vast array of marine species. Furthermore, seawater warming is facilitating the arrival and spread of new thermophilic species, posing a severe threat to biodiversity. Among the species
Externí odkaz:
https://doaj.org/article/10e0d4e278ff43948171b6257c40af4f
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 regularizatio
Externí odkaz:
http://arxiv.org/abs/2110.00124