Alfio Ferrara
YOU?
Author Swipe
View article: The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models
The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models Open
Text-to-image diffusion models have demonstrated remarkable capabilities in generating artistic content by learning from billions of images, including popular artworks. However, the fundamental question of how these models internally repre…
View article: Incremental Affinity Propagation Based on Cluster Consolidation and Stratification
Incremental Affinity Propagation Based on Cluster Consolidation and Stratification Open
Modern data mining applications require to perform incremental clustering over dynamic datasets by tracing temporal changes over the resulting clusters. In this paper, we propose A-Posteriori affinity Propagation (APP), an incremental exte…
View article: Unveiling Transformer Perception by Exploring Input Manifolds
Unveiling Transformer Perception by Exploring Input Manifolds Open
This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical theory which describes the internal layers of a Transformer ar…
View article: Studying word meaning evolution through incremental semantic shift detection
Studying word meaning evolution through incremental semantic shift detection Open
The study of semantic shift , that is, of how words change meaning as a consequence of social practices, events and political circumstances, is relevant in Natural Language Processing, Linguistics, and Social Sciences. The increasing avail…
View article: LiMe: a Latin Corpus of Late Medieval Criminal Sentences
LiMe: a Latin Corpus of Late Medieval Criminal Sentences Open
The Latin language has received attention from the computational linguistics research community, which has built, over the years, several valuable resources, ranging from detailed annotated corpora to sophisticated tools for linguistic ana…
View article: How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models
How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models Open
In this paper, we explore the idea of analysing the historical bias of contextual language models based on BERT by measuring their adequacy with respect to Early Modern (EME) and Modern (ME) English. In our preliminary experiments, we perf…
View article: Incremental Affinity Propagation based on Cluster Consolidation and Stratification
Incremental Affinity Propagation based on Cluster Consolidation and Stratification Open
Modern data mining applications require to perform incremental clustering over dynamic datasets by tracing temporal changes over the resulting clusters. In this paper, we propose A-Posteriori affinity Propagation (APP), an incremental exte…
View article: The Gender Gap in Issue Attention and Language Use within a Legislative Setting: An Application to the Italian Parliament (1948–2020)
The Gender Gap in Issue Attention and Language Use within a Legislative Setting: An Application to the Italian Parliament (1948–2020) Open
We investigate the gender gap in issue attention among members of parliament (MPs) by applying automated text analytic techniques to a novel data set on Italian parliamentary speeches over a remarkably long period (1948–2020). We detect a …
View article: Studying Word Meaning Evolution through Incremental Semantic Shift Detection: A Case Study of Italian Parliamentary Speeches
Studying Word Meaning Evolution through Incremental Semantic Shift Detection: A Case Study of Italian Parliamentary Speeches Open
The study of semantic shifts, that is, of how words change meaning as a consequence of social practices, events and political circumstances, is relevant in Natural Language Processing, Linguistics, and Social Sciences. The increasing avail…
View article: Studying Word Meaning Evolution through Incremental Semantic Shift Detection: A Case Study of Italian Parliamentary Speeches
Studying Word Meaning Evolution through Incremental Semantic Shift Detection: A Case Study of Italian Parliamentary Speeches Open
The study of semantic shifts, that is, of how words change meaning as a consequence of social practices, events and political circumstances, is relevant in Natural Language Processing, Linguistics, and Social Sciences. The increasing avail…
View article: Participatory Citizen Curation in the VAST Project Framework
Participatory Citizen Curation in the VAST Project Framework Open
In this paper, we present a participatory approach to citizen curation developed in the framework of the EU H2020 VAST (Values Across Space and Time) project. VAST focuses on the transformation of values across space and time, with particu…
View article: Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE
Augustine of Hippo at SemEval-2023 Task 4: An Explainable Knowledge Extraction Method to Identify Human Values in Arguments with SuperASKE Open
In this paper we present and discuss the results achieved by the "Augustine of Hippo" team at SemEval-2023 Task 4 about human value detection.In particular, we provide a quantitative and qualitative reviews of the results obtained by Super…
View article: What is Done is Done: an Incremental Approach to Semantic Shift Detection
What is Done is Done: an Incremental Approach to Semantic Shift Detection Open
Contextual word embedding techniques for semantic shift detection are receiving more and more attention. In this paper, we present What is Done is Done (WiDiD), an incremental approach to semantic shift detection based on incremental clust…
View article: A Computational History Approach to Interpretation and Analysis of Moral European Values: the VAST Research Project
A Computational History Approach to Interpretation and Analysis of Moral European Values: the VAST Research Project Open
The rapid development and diffusion of artificial intelligence and data science techniques enable research in the field of humanities and social sciences to become more and more computational. In this paper, we present the computational hi…
View article: From Digital to Computational Humanities: The VAST Project Vision
From Digital to Computational Humanities: The VAST Project Vision Open
In the shift from Digital to Computational Humanities, the role of artificial intelligence, data scienceand digital technologies is fundamental to achieve advances and results. As a concrete example ofComputational Humanities Research, we …
View article: An Explainable Probabilistic Classifier for Categorical Data Inspired to Quantum Physics
An Explainable Probabilistic Classifier for Categorical Data Inspired to Quantum Physics Open
This paper presents Sparse Tensor Classifier (STC), a supervised classification algorithm for categorical data inspired by the notion of superposition of states in quantum physics. By regarding an observation as a superposition of features…
View article: The Milano Sforza Registers of the Dead: Health Policies in Italian Renaissance
The Milano Sforza Registers of the Dead: Health Policies in Italian Renaissance Open
The institution of the Liber Mortuorum in Milan greatly anticipates death registrations in Europe. Introduced in 1450 by Duke Francesco Sforza for the early containment of plague it was daily compiled until 1801, reporting demographical da…
View article: Improving the Accuracy of Automatic Facial Expression Recognition in Speaking Subjects with Deep Learning
Improving the Accuracy of Automatic Facial Expression Recognition in Speaking Subjects with Deep Learning Open
When automatic facial expression recognition is applied to video sequences of speaking subjects, the recognition accuracy has been noted to be lower than with video sequences of still subjects. This effect known as the speaking effect aris…
View article: Crowd-assessing quality in uncertain data linking datasets
Crowd-assessing quality in uncertain data linking datasets Open
The quality of a dataset used for evaluating data linking methods, techniques, and tools depends on the availability of a set of mappings, called reference alignment , that is known to be correct. In particular, it is crucial that mappings…
View article: Results of the Ontology Alignment Evaluation Initiative 2019
Results of the Ontology Alignment Evaluation Initiative 2019 Open
The Ontology Alignment Evaluation Initiative (OAEI) aims at comparing ontology matching systems on precisely defined test cases. These test cases can be based on ontologies of different levels of complexity (from simple thesauri to express…
View article: Results of the ontology alignment evaluation initiative 2017
Results of the ontology alignment evaluation initiative 2017 Open
Ontology matching consists of finding correspondences between semantically related entities of different ontologies. The Ontology Alignment Evaluation Initiative (OAEI) aims at comparing ontology matching systems on precisely defined test …
View article: Unsupervised Detection of Argumentative Units though Topic Modeling Techniques
Unsupervised Detection of Argumentative Units though Topic Modeling Techniques Open
Publication in the conference proceedings of SampTA, Bremen, Germany, 2013