ATTANASIO, GIUSEPPE
ATTANASIO, GIUSEPPE
Dipartimento di Scienze delle Decisioni
A tale of pronouns: interpretability informs gender bias mitigation for fairer instruction-tuned machine translation
2023 Attanasio, Giuseppe; Plaza del Arco, Flor; Nozza, Debora; Lauscher, Anne
Benchmarking post-hoc interpretability approaches for transformer-based misogyny detection
2022 Attanasio, Giuseppe; Nozza, Debora; Pastor, Eliana; Hovy, Dirk
Classist Tools: Social Class Correlates with Performance in NLP
2024 Cercas Curry, Amanda; Attanasio, Giuseppe; Talat, Zeerak; Hovy, Dirk
Entropy-based attention regularization frees unintended bias mitigation from lists
2022 Attanasio, Giuseppe; Nozza, Debora; Hovy, Dirk; Baralis, Elena
ferret: a framework for benchmarking explainers on transformers
2023 Attanasio, Giuseppe; Pastor, Eliana; Di Bonaventura, Chiara; Nozza, Debora
HATE-ITA: hate speech detection in Italian social media text
2022 Nozza, Debora; Bianchi, Federico; Attanasio, Giuseppe
Is it really that simple? Prompting Language Models for Automatic Text Simplification in Italian
2023 Nozza, Debora; Attanasio, Giuseppe
Metrics for what, metrics for whom: assessing actionability of bias evaluation metrics in NLP
2024 Delobelle, Pieter; Attanasio, Giuseppe; Nozza, Debora; Blodgett, Su Lin; Talat, Zeerak
MilaNLP at SemEval-2022 Task 5: using perceiver IO for detecting misogynous memes with text and image modalities
2022 Attanasio, Giuseppe; Nozza, Debora; Bianchi, Federico
MilaNLP at SemEval-2023 Task 10: ensembling domain-adapted and regularized pretrained language models for robust sexism detection
2023 Curry, Amanda Cercas; Attanasio, Giuseppe; Nozza, Debora; Hovy, Dirk
Twists, humps, and pebbles: multilingual speech recognition models exhibit gender performance gaps
2024 Attanasio, Giuseppe; Savoldi, Beatrice; Fucci, Dennis; Hovy, Dirk
Weigh your own words: improving hate speech counter narrative generation via attention regularization
2023 Bonaldi, Helena; Attanasio, Giuseppe; Nozza, Debora; Guerini, Marco
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
2024 Röttger, Paul; Kirk, Hannah; Vidgen, Bertie; Attanasio, Giuseppe; Bianchi, Federico; Hovy, Dirk
| Titolo | Data di pubblicazione | Autore(i) | Rivista | Editore |
|---|---|---|---|---|
| A tale of pronouns: interpretability informs gender bias mitigation for fairer instruction-tuned machine translation | 1-gen-2023 | Attanasio, Giuseppe; Plaza del Arco, Flor; Nozza, Debora; Lauscher, Anne | - | Association for Computational Linguistics |
| Benchmarking post-hoc interpretability approaches for transformer-based misogyny detection | 1-gen-2022 | Attanasio, Giuseppe; Nozza, Debora; Pastor, Eliana; Hovy, Dirk | - | Association for Computational Linguistics |
| Classist Tools: Social Class Correlates with Performance in NLP | 1-gen-2024 | Cercas Curry, Amanda; Attanasio, Giuseppe; Talat, Zeerak; Hovy, Dirk | - | Association for Computational Linguistics |
| Entropy-based attention regularization frees unintended bias mitigation from lists | 1-gen-2022 | Attanasio, Giuseppe; Nozza, Debora; Hovy, Dirk; Baralis, Elena | - | Association for Computational Linguistics |
| ferret: a framework for benchmarking explainers on transformers | 1-gen-2023 | Attanasio, Giuseppe; Pastor, Eliana; Di Bonaventura, Chiara; Nozza, Debora | - | Association for Computational Linguistics |
| HATE-ITA: hate speech detection in Italian social media text | 1-gen-2022 | Nozza, Debora; Bianchi, Federico; Attanasio, Giuseppe | - | Association for Computational Linguistics |
| Is it really that simple? Prompting Language Models for Automatic Text Simplification in Italian | 1-gen-2023 | Nozza, Debora; Attanasio, Giuseppe | - | (seleziona...) |
| Metrics for what, metrics for whom: assessing actionability of bias evaluation metrics in NLP | 1-gen-2024 | Delobelle, Pieter; Attanasio, Giuseppe; Nozza, Debora; Blodgett, Su Lin; Talat, Zeerak | - | Association for Computational Linguistics |
| MilaNLP at SemEval-2022 Task 5: using perceiver IO for detecting misogynous memes with text and image modalities | 1-gen-2022 | Attanasio, Giuseppe; Nozza, Debora; Bianchi, Federico | - | Association for Computational Linguistics |
| MilaNLP at SemEval-2023 Task 10: ensembling domain-adapted and regularized pretrained language models for robust sexism detection | 1-gen-2023 | Curry, Amanda Cercas; Attanasio, Giuseppe; Nozza, Debora; Hovy, Dirk | - | Association for Computational Linguistics |
| Twists, humps, and pebbles: multilingual speech recognition models exhibit gender performance gaps | 1-gen-2024 | Attanasio, Giuseppe; Savoldi, Beatrice; Fucci, Dennis; Hovy, Dirk | - | Association for Computational Linguistics |
| Weigh your own words: improving hate speech counter narrative generation via attention regularization | 1-gen-2023 | Bonaldi, Helena; Attanasio, Giuseppe; Nozza, Debora; Guerini, Marco | - | Association for Computational Linguistics |
| XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models | 1-gen-2024 | Röttger, Paul; Kirk, Hannah; Vidgen, Bertie; Attanasio, Giuseppe; Bianchi, Federico; Hovy, Dirk | - | Association for Computational Linguistics |