Marta Marchiori Manerba

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 12

Top Topics

Data Generation

Top Venues

xAI (Late-breaking Work, Demos, Doctoral Consortium)

NLPerspectives@LREC

Publications

Eleonora Cappuccio, Isacco Beretta, Marta Marchiori Manerba, Salvatore Rinzivillo
An Interactive Interface for Feature Space Navigation. HHAI (2024)
Mattia Setzu, Marta Marchiori Manerba, Pasquale Minervini, Debora Nozza
FairBelief - Assessing Harmful Beliefs in Language Models. CoRR (2024)
Luca Nannini, Marta Marchiori Manerba, Isacco Beretta
Mapping the landscape of ethical considerations in explainable AI research. Ethics Inf. Technol. 26 (3) (2024)
Federico Mazzoni, Marta Marchiori Manerba, Martina Cinquini, Riccardo Guidotti, Salvatore Ruggieri
GenFair: A Genetic Fairness-Enhancing Data Generation Framework. DS (2023)
Isacco Beretta, Eleonora Cappuccio, Marta Marchiori Manerba
User-Driven Counterfactual Generator: A Human Centered Exploration. xAI (Late-breaking Work, Demos, Doctoral Consortium) (2023)
Marta Marchiori Manerba
Fairness Auditing, Explanation and Debiasing in Linguistic Data and Language Models. xAI (Late-breaking Work, Demos, Doctoral Consortium) (2023)
Marta Marchiori Manerba, Karolina Stanczak, Riccardo Guidotti, Isabelle Augenstein
Social Bias Probing: Fairness Benchmarking for Language Models. CoRR (2023)
Marta Marchiori Manerba, Virginia Morini
Exposing Racial Dialect Bias in Abusive Language Detection: Can Explainability Play a Role? PKDD/ECML Workshops (1) (2022)
Marta Marchiori Manerba, Riccardo Guidotti, Lucia C. Passaro, Salvatore Ruggieri
Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset. NLPerspectives@LREC (2022)
Marta Marchiori Manerba, Riccardo Guidotti
Investigating Debiasing Effects on Classification and Explainability. AIES (2022)
Arianna Muti, Marta Marchiori Manerba, Katerina Korre, Alberto Barrón-Cedeño
LeaningTower@LT-EDI-ACL2022: When Hope and Hate Collide. LT-EDI (2022)
Marta Marchiori Manerba, Riccardo Guidotti
FairShades: Fairness Auditing via Explainability in Abusive Language Detection Systems. CogMI (2021)