9 papers
Geometry-Aware Bayesian Quantification via Compositional Data Analysis
Alejandro Moreo, Pablo González, Juan José del Coz
Accurately estimating the unknown target label distribution is the critical first step for adapting to label shift. This task, widely known as quantification or class prevalence es…
Efficient quantification on large-scale networks
Alessio Micheli, Alejandro Moreo, Marco Podda +3
Network quantification (NQ) is the problem of estimating the proportions of nodes belonging to each class in subsets of unlabelled graph nodes. When prior probability shift is at p…
Typoglycemia under the Hood: Investigating Language Models' Understanding of Scrambled Words
Gianluca Sperduti, Alejandro Moreo
Research in linguistics has shown that humans can read words with internally scrambled letters, a phenomenon recently dubbed typoglycemia. Some specific NLP models have recently be…
Misspellings in Natural Language Processing: A survey
Gianluca Sperduti, Alejandro Moreo
This survey provides an overview of the challenges of misspellings in natural language processing (NLP). While often unintentional, misspellings have become ubiquitous in digital c…
Quantifying Feature Importance for Online Content Moderation
Benedetta Tessa, Alejandro Moreo, Stefano Cresci +2
Accurately estimating how users respond to moderation interventions is paramount for developing effective and user-centred moderation strategies. However, this requires a clear und…
Transductive Model Selection under Prior Probability Shift
Lorenzo Volpi, Alejandro Moreo, Fabrizio Sebastiani
Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are…