???global.info.a_carregar???
Identificação

Identificação pessoal

Nome completo
GIUSEPPE ATTANASIO

Nomes de citação

  • ATTANASIO, GIUSEPPE

Identificadores de autor

Ciência ID
CB1B-6E95-2BB8
ORCID iD
0000-0001-6945-3698

Endereços de correio eletrónico

  • gattanasio.work@gmail.com (Profissional)

Websites

Domínios de atuação

  • Ciências da Engenharia e Tecnologias - Engenharia Eletrotécnica, Eletrónica e Informática

Idiomas

Idioma Conversação Leitura Escrita Compreensão Peer-review
Italiano (Idioma materno)
Espanhol; Castelhano Utilizador elementar (A2) Utilizador elementar (A2) Utilizador elementar (A1) Utilizador elementar (A2) Utilizador elementar (A1)
Português Utilizador elementar (A2) Utilizador independente (B1) Utilizador elementar (A2) Utilizador independente (B1) Utilizador elementar (A1)
Inglês Utilizador proficiente (C2) Utilizador proficiente (C2) Utilizador proficiente (C2) Utilizador proficiente (C2) Utilizador proficiente (C2)
Formação
Grau Classificação
2018/11/01 - 2022/01/31
Concluído
 Computer and Control Engineering (Dottorato di Ricerca)
Politecnico di Torino Facoltà di Ingegneria, Itália
"Dissecting Deep Language Models: The Explainability and Bias Perspective" (TESE/DISSERTAÇÃO)
2018
Concluído
 Computer Engineering (Laurea Magistrale)
Politecnico di Torino, Itália
2016
Concluído
 Computer Engineering (Laurea)
Politecnico di Torino, Itália
Percurso profissional

Ciência

Categoria Profissional
Instituição de acolhimento 		Empregador
2024/01/16 - Atual Pós-doutorado (Investigação) Instituto de Telecomunicações Lisboa, Portugal
2022/01/01 - 2024/02/15 Pós-doutorado (Investigação) Università Bocconi, Itália
Projetos

Bolsa

Designação Financiadores
2026/02/01 - 2027/02/01 SMURF4EU: A Suite of Multimodal Reasoning Foundation Models for Europe
SMURF4EU
Co-Investigador Responsável (Co-IR)
Em curso
2025/05/31 - 2026/05/31 Ouvia: A User-Centered Benchmark for Usability Assessment of Speech Translation Systems.
Ouvia
Investigador responsável
European Association for Machine Translation
Em curso
2025/05/31 - 2026/05/31 MELT: Multilingual Efficient Learning for Speech-Text Models
MELT
Investigador responsável
Fundação para a Ciência e a Tecnologia
Em curso
2024/02/01 - 2025/02/01 GeFMT: Gender-Fair Language in German Machine Translation.
GeFMT
Co-Investigador Responsável (Co-IR)
European Association for Machine Translation
Concluído
2023/03/01 - 2024/03/01 ItaLLM: Advancing Beyond-English Language Models: A Computational Framework for Italian Language Modeling
ItaLLM
Investigador responsável
Cineca
Concluído
Produções

Publicações

Artigo em conferência
  1. Attanasio, Giuseppe; Savoldi, Beatrice; Fucci, Dennis; Hovy, Dirk. "Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps". 2024.
    10.18653/v1/2024.emnlp-main.1188
  2. Delobelle, Pieter; Attanasio, Giuseppe; Nozza, Debora; Blodgett, Su Lin; Talat, Zeerak. "Metrics for What, Metrics for Whom: Assessing Actionability of Bias Evaluation Metrics in NLP". 2024.
    10.18653/v1/2024.emnlp-main.1207
  3. Cercas Curry, Amanda; Attanasio, Giuseppe; Talat, Zeerak; Hovy, Dirk. "Classist Tools: Social Class Correlates with Performance in NLP". 2024.
    10.18653/v1/2024.acl-long.682
  4. Röttger, Paul; Kirk, Hannah; Vidgen, Bertie; Attanasio, Giuseppe; Bianchi, Federico; Hovy, Dirk. "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models". 2024.
    10.18653/v1/2024.naacl-long.301
  5. Lardelli, Manuel; Attanasio, Giuseppe; Lauscher, Anne. "Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation into German". 2024.
    10.18653/v1/2024.findings-acl.448
  6. Bianchi, Federico; Suzgun, Mirac ; ATTANASIO, GIUSEPPE; Röttger, Paul; Jurafsky, Dan; Hashimoto, Tatsunori; Zou, James. "Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions". Trabalho apresentado em The Twelfth International Conference on Learning Representations, 2024.
  7. Pastor, E.; Koudounas, A.; Attanasio, G.; Hovy, D.; Baralis, E.. "Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features". 2024.
    10.48550/arXiv.2309.07733
  8. Bianchi, F.; Suzgun, M.; Attanasio, G.; Röttger, P.; Jurafsky, D.; Hashimoto, T.; Zou, J.. "SAFETY-TUNED LLAMAS: LESSONS FROM IMPROVING THE SAFETY OF LARGE LANGUAGE MODELS THAT FOLLOW INSTRUCTIONS". 2024.
    10.48550/arXiv.2309.07875
  9. Pernisi, F.; Attanasio, G.; Nozza, D.. "MONICA: Monitoring Coverage and Attitudes of Italian Measures in Response to COVID-19". 2024.
  10. Attanasio, G.; Basile, P.; Borazio, F.; Croce, D.; Francis, M.; Gili, J.; Musacchio, E.; et al. "CALAMITA: Challenge the Abilities of LAnguage Models in ITAlian". 2024.
  11. Lardelli, M.; Lauscher, A.; Attanasio, G.. "GeFMT: Gender-Fair Language in German Machine Translation". 2024.
  12. Attanasio, G.; La Quatra, M.; Santilli, A.; Savoldi, B.. "ItaEval: A CALAMITA Challenge". 2024.
  13. Attanasio, G.; Delobelle, P.; Quatra, M.L.; Santilli, A.; Savoldi, B.. "ItaEval and TweetyIta: A New Extensive Benchmark and Efficiency-First Language Model for Italian". 2024.
  14. Zerva, C.; Blain, F.; de Souza, J.G.C.; Kanojia, D.; Deoghare, S.; Guerreiro, N.M.; Attanasio, G.; et al. "Findings of the Quality Estimation Shared Task at WMT 2024 Are LLMs Closing the Gap in QE?". 2024.
  15. Lardelli, M.; Dill, T.; Attanasio, G.; Lauscher, A.. "Sparks of Fairness: Preliminary Evidence of Commercial Machine Translation as English-to-German Gender-Fair Dictionaries". 2024.
  16. Koudounas, A.; Pastor, E.; Attanasio, G.; de Alfaro, L.; Baralis, E.. "PRIORITIZING DATA ACQUISITION FOR END-TO-END SPEECH MODEL IMPROVEMENT". 2024.
    10.1109/ICASSP48485.2024.10446326
  17. Koudounas, A.; Pastor, E.; Mazzia, V.; Giollo, M.; Gueudre, T.; Reale, E.; Attanasio, G.; et al. "Leveraging Confidence Models for Identifying Challenging Data Subgroups in Speech Models". 2024.
    10.1109/ICASSPW62465.2024.10626001
  18. Attanasio, Giuseppe; Plaza del Arco, Flor; Nozza, Debora; Lauscher, Anne. "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation". 2023.
    10.18653/v1/2023.emnlp-main.243
  19. Attanasio, Giuseppe; Pastor, Eliana; Di Bonaventura, Chiara; Nozza, Debora. "ferret: a Framework for Benchmarking Explainers on Transformers". 2023.
    10.18653/v1/2023.eacl-demo.29
  20. Nozza, D.; Attanasio, G.. "Is It Really That Simple? Prompting Language Models for Automatic Text Simplification in Italian". 2023.
  21. Bianchi, F.; Attanasio, G.; Pisoni, R.; Terragni, S.; Sarti, G.; Balestri, D.. "Contrastive Language-Image Pre-training for the Italian Language". 2023.
    10.48550/arxiv.2108.08688
  22. Bonaldi, H.; Attanasio, G.; Nozza, D.; Guerini, M.. "Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization". 2023.
    10.48550/arXiv.2309.02311
  23. Attanasio, G.; Pastor, E.; Di Bonaventura, C.; Nozza, D.. "ferret: a Framework for Benchmarking Explainers on Transformers". 2023.
    10.48550/arXiv.2208.01575
  24. Curry, A.C.; Attanasio, G.; Nozza, D.; Hovy, D.. "MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection". 2023.
  25. Koudounas, A.; Pastor, E.; Attanasio, G.; Mazzia, V.; Giollo, M.; Gueudre, T.; Cagliero, L.; et al. "Exploring Subgroup Performance in End-to-End Speech Models". 2023.
    10.1109/ICASSP49357.2023.10095284
  26. Attanasio, Giuseppe; Nozza, Debora; Hovy, Dirk; Baralis, Elena. "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists". 2022.
    10.18653/v1/2022.findings-acl.88
  27. Nozza, D.; Bianchi, F.; Attanasio, G.. "HATE-ITA: Hate Speech Detection in Italian Social Media Text". 2022.
    10.18653/v1/2022.woah-1.24
  28. Tagliabue, J.; Bianchi, F.; Schnabel, T.; Attanasio, G.; Greco, C.; Moreira, G.D.S.P.; Chia, P.J.. "EvalRS: a rounded evaluation of recommender systems". 2022.
    10.48550/arXiv.2207.05772
  29. Attanasio, G.; Nozza, D.; Pastor, E.; Hovy, D.. "Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection". 2022.
  30. Attanasio, G.; Nozza, D.; Bianchi, F.. "MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities". 2022.
  31. Attanasio, G.; Greco, S.; La Quatra, M.; Cagliero, L.; Tonti, M.; Cerquitelli, T.; Raus, R.. "E-MIMIC: Empowering Multilingual Inclusive Communication". 2021.
    10.1109/BigData52589.2021.9671868
  32. Attanasio, G.; Giobergia, F.; Pasini, A.; Ventura, F.; Baralis, E.; Cagliero, L.; Garza, P.; et al. "DSLE: A Smart Platform for Designing Data Science Competitions". 2020.
    10.1109/COMPSAC48688.2020.00026
  33. Attanasio, G.; Cagliero, L.; Baralis, E.. "Leveraging the explainability of associative classifiers to support quantitative stock trading". 2020.
    10.1145/3401832.3402679
  34. Attanasio, G.; Pastor, E.. "PoliTeam @ AMI: Improving sentence embedding similarity with misogyny lexicons for automatic misogyny identification in Italian tweets". 2020.
  35. Attanasio, G.; Cagliero, L.; Garza, P.; Baralis, E.. "Combining news sentiment and technical analysis to predict stock trend reversal". 2019.
    10.1109/ICDMW.2019.00079
  36. Attanasio, G.; Garza, P.; Cagliero, L.; Baralis, E.. "Quantitative cryptocurrency trading: Exploring the use of machine learning techniques". 2019.
    10.1145/3336499.3338003
  37. Attanasio, G.; Cannavò, A.; Cibrario, F.; Lamberti, F.; Montuschi, P.; Paravati, G.. "HOT: Hold your own tools for AR-based constructive art". 2017.
    10.1109/3DUI.2017.7893369
Artigo em revista
  1. Alkis Koudounas; Eliana Pastor; Giuseppe Attanasio; Vittorio Mazzia; Manuel Giollo; Thomas Gueudre; Elisa Reale; et al. "Towards Comprehensive Subgroup Performance Analysis in Speech Models". IEEE/ACM Transactions on Audio, Speech, and Language Processing (2024): https://doi.org/10.1109/TASLP.2024.3363447.
    10.1109/TASLP.2024.3363447
  2. Tagliabue, J.; Bianchi, F.; Schnabel, T.; Attanasio, G.; Greco, C.; de Souza Moreira, G.; Chia, P.J.. "Correction to: A challenge for rounded evaluation of recommender systems (Nature Machine Intelligence, (2023), 5, 2, (181-182), 10.1038/s42256-022-00606-0)". Nature Machine Intelligence 6 3 (2024): 368-368. http://www.scopus.com/inward/record.url?eid=2-s2.0-85187141499&partnerID=MN8TOARS.
    10.1038/s42256-024-00819-5
  3. Chia, Patrick John; Attanasio, Giuseppe; Bianchi, Federico; Terragni, Silvia; Magalhães, Ana Rita; Goncalves, Diogo; Greco, Ciro; Tagliabue, Jacopo. "Contrastive language and vision learning of general fashion concepts". Scientific Reports 13 1 (2023): https://doi.org/10.1038/s41598-022-26364-y.
    10.1038/s41598-022-26364-y
  4. Tagliabue, J.; Bianchi, F.; Schnabel, T.; Attanasio, G.; Greco, C.; de Souza Moreira, G.; Chia, P.J.. "A challenge for rounded evaluation of recommender systems". Nature Machine Intelligence 5 2 (2023): 181-182. http://www.scopus.com/inward/record.url?eid=2-s2.0-85146878003&partnerID=MN8TOARS.
    10.1038/s42256-022-00606-0
  5. Chia, P.J.; Attanasio, G.; Bianchi, F.; Terragni, S.; Magalhães, A.R.; Goncalves, D.; Greco, C.; Tagliabue, J.. "Contrastive language and vision learning of general fashion concepts". Scientific Reports 12 1 (2022): http://www.scopus.com/inward/record.url?eid=2-s2.0-85141619688&partnerID=MN8TOARS.
    10.48550/arXiv.2204.03972
  6. Cagliero, Luca; Garza, Paolo; Attanasio, Giuseppe; Baralis, Elena. "Training ensembles of faceted classification models for quantitative stock trading". Computing 102 5 (2020): 1213-1225. https://doi.org/10.1007/s00607-019-00776-7.
    10.1007/s00607-019-00776-7
Pré-impressão
  1. Giovanni Cassani; Federico Bianchi; Giuseppe Attanasio; Marco Marelli; Fritz Guenther. "Meaning Modulations and Stability in Large Language Models: An Analysis of BERT Embeddings for Psycholinguistic Research". 2023. https://doi.org/10.31234/osf.io/b45ys.
    10.31234/osf.io/b45ys

Outros

Outra produção
  1. MSTS: A Multimodal Safety Test Suite for Vision-Language Models. 2025. Röttger, P.; Attanasio, G.; Friedrich, F.; Goldzycher, J.; Parrish, A.; Bhardwaj, R.; Di Bonaventura, C.; et al. http://www.scopus.com/inward/record.url?eid=2-s2.0-85216601299&partnerID=MN8TOARS.
    10.48550/arXiv.2501.10057
  2. Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation. 2024. Zaranis, E.; Attanasio, G.; Agrawal, S.; Martins, A.F.T.. http://www.scopus.com/inward/record.url?eid=2-s2.0-105003129918&partnerID=MN8TOARS.
    10.48550/arXiv.2410.10995
  3. ITALIC: An Italian Intent Classification Dataset. 2023. Koudounas, A.; Quatra, M.L.; Vaiani, L.; Colomba, L.; Attanasio, G.; Pastor, E.; Cagliero, L.; Baralis, E.. http://www.scopus.com/inward/record.url?eid=2-s2.0-85163815619&partnerID=MN8TOARS.
    10.21437/Interspeech.2023-1980
  4. E Pluribus Unum: Guidelines on Multi-Objective Evaluation of Recommender Systems. 2023. Chia, P.J.; Attanasio, G.; Tagliabue, J.; Bianchi, F.; Greco, C.; de Souza P. Moreira, G.; Eynard, D.; Husain, F.. http://www.scopus.com/inward/record.url?eid=2-s2.0-85160197327&partnerID=MN8TOARS.
    10.48550/arXiv.2304.10621
  5. Is It Worth the (Environmental) Cost? Limited Evidence for Temporal Adaptation via Continuous Training. 2022. Attanasio, G.; Nozza, D.; Bianchi, F.; Hovy, D.. http://www.scopus.com/inward/record.url?eid=2-s2.0-85163851601&partnerID=MN8TOARS.
Atividades

Orientação

Título / Tema
Papel desempenhado 		Curso (Tipo)
Instituição / Organização
2023 - Atual Efficient speech and vision multimodal and multilingual adaptation of language models.
Coorientador
Distinções

Prémio

2024 Social Impact Paper Award at EMNLP 2024
2023 Best Student Paper Award