Debora Nozza

Dr. Debora Nozza

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 June 2023
Verified
Conference Paper
Open access
FBFederico Bianchi
Federico Bianchi
PKPratyusha Kalluri
Pratyusha Kalluri
EDEsin Durmus
Esin Durmus
FLFaisal Ladhak
Faisal Ladhak
MCMyra Cheng
Myra Cheng
ACAylin Caliskan
Aylin Caliskan
Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects. For example, we find cases of prompting for basic traits or social roles resulting in images reinforcing whiteness as ideal, prompting for occupations resulting in amplification of racial and gender disparities, and prompting for objects resulting in reification of American norms. Stereotypes are present regardless of whether prompts explicitly mention identity and demographic language or avoid such language. Moreover, stereotypes persist despite mitigation strategies; neither user attempts to counter stereotypes by requesting images with specific counter-stereotypes nor institutional attempts to add system “guardrails” have prevented the perpetuation of stereotypes. Our analysis justifies concerns regarding the impacts of today’s models, presenting striking exemplars, and connecting these findings with deep insights into harms drawn from social scientific and humanist disciplines. This work contributes to the effort to shed light on the uniquely complex biases in language-vision models and demonstrates the ways that the mass deployment of text-to-image generation models results in mass dissemination of stereotypes and resulting harms.

1 November 2016
Verified
Conference Paper
Closed access
DNDebora Nozza
Debora Nozza
EFElisabetta Fersini
Elisabetta Fersini
EMEnza Messina
Enza Messina
Real world applications of machine learning in natural language processing can span many different domains and usually require a huge effort for the annotation of domain specific training data. For this reason, domain adaptation techniques have gained a lot of attention in the last years. In order to derive an effective domain adaptation, a good feature representation across domains is crucial as well as the generalisation ability of the predictive model. In this paper we address the problem of domain adaptation for sentiment classification by combining deep learning, for acquiring a cross-domain high-level feature representation, and ensemble methods, for reducing the cross-domain generalization error. The proposed adaptation framework has been evaluated on a benchmark dataset composed of reviews of four different Amazon category of products, significantly outperforming the state of the art methods.

1 January 2023
Verified
Conference Paper
Open access
PDF file
DNDebora Nozza
Debora Nozza
DHDirk Hovy
Dirk Hovy
Debora Nozza, Dirk Hovy. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

1 January 2022
Verified
Conference Paper
Open access
PDF file
STSamia Touileb
Samia Touileb
DNDebora Nozza
Debora Nozza
Samia Touileb, Debora Nozza. Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS). 2022.

1 May 2020 in Information Sciences
Verified
Journal Article
Closed access
DNDebora Nozza
Debora Nozza
EFElisabetta Fersini
Elisabetta Fersini
EMEnza Messina
Enza Messina

1 January 2023
Verified
Conference Paper
Open access
PDF file
DLDavide Locatelli
Davide Locatelli
GDGreta Damo
Greta Damo
DNDebora Nozza
Debora Nozza
Davide Locatelli, Greta Damo, Debora Nozza. Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). 2023.