Language models for text-to-image generation can output good quality images when referential aspects of pictures are evaluated. The generation of creative images is not under scrutiny at the moment, but it poses interesting challenges: should we expect more creative images using more creative prompts? What is the relationship between prompts and images in the global process of human evaluation? In this paper, we want to highlight several criteria that should be taken into account for building a creative text-to-image generation benchmark, collecting insights from multiple disciplines (e.g., linguistics, cognitive psychology, philosophy, psychology of art).
Creative Text-to-Image Generation: Suggestions for a Benchmark
Russo, Irene
Primo
2022
Abstract
Language models for text-to-image generation can output good quality images when referential aspects of pictures are evaluated. The generation of creative images is not under scrutiny at the moment, but it poses interesting challenges: should we expect more creative images using more creative prompts? What is the relationship between prompts and images in the global process of human evaluation? In this paper, we want to highlight several criteria that should be taken into account for building a creative text-to-image generation benchmark, collecting insights from multiple disciplines (e.g., linguistics, cognitive psychology, philosophy, psychology of art).| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | en |
| dc.authority.people | Russo, Irene | en |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.area | Non assegn | * |
| dc.date.accessioned | 2024/07/22 16:34:05 | - |
| dc.date.available | 2024/07/22 16:34:05 | - |
| dc.date.firstsubmission | 2024/06/12 12:42:24 | * |
| dc.date.issued | 2022 | - |
| dc.date.submission | 2025/03/07 09:00:45 | * |
| dc.description.abstracteng | Language models for text-to-image generation can output good quality images when referential aspects of pictures are evaluated. The generation of creative images is not under scrutiny at the moment, but it poses interesting challenges: should we expect more creative images using more creative prompts? What is the relationship between prompts and images in the global process of human evaluation? In this paper, we want to highlight several criteria that should be taken into account for building a creative text-to-image generation benchmark, collecting insights from multiple disciplines (e.g., linguistics, cognitive psychology, philosophy, psychology of art). | - |
| dc.description.allpeople | Russo, Irene | - |
| dc.description.allpeopleoriginal | Russo, Irene | en |
| dc.description.fulltext | open | en |
| dc.description.international | no | en |
| dc.description.numberofauthors | 1 | - |
| dc.identifier.isbn | 978-1-955917-75-9 | en |
| dc.identifier.source | bibtex | * |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/475282 | - |
| dc.identifier.url | https://aclanthology.org/2022.nlp4dh-1.18 | en |
| dc.language.iso | eng | en |
| dc.publisher.name | Association for Computational Linguistics | en |
| dc.relation.alleditors | Hamalainen, Mika and Alnajjar, Khalid and Partanen, Niko and Rueter, Jack | en |
| dc.relation.conferencename | Workshop on Natural Language Processing for Digital Humanities | en |
| dc.relation.firstpage | 145 | en |
| dc.relation.ispartofbook | Proceedings of the 2nd International Workshop on Natural Language Processing for Digital Humanities | en |
| dc.relation.lastpage | 154 | en |
| dc.relation.numberofpages | 10 | en |
| dc.subject.keywordseng | artificial creativity, text-to-image models | - |
| dc.subject.singlekeyword | artificial creativity | * |
| dc.subject.singlekeyword | text-to-image models | * |
| dc.title | Creative Text-to-Image Generation: Suggestions for a Benchmark | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| iris.mediafilter.data | 2025/04/03 03:56:43 | * |
| iris.orcid.lastModifiedDate | 2025/03/07 14:13:26 | * |
| iris.orcid.lastModifiedMillisecond | 1741353206045 | * |
| iris.sitodocente.maxattempts | 1 | - |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
2022.nlp4dh-1.18 (1).pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Creative commons
Dimensione
2.15 MB
Formato
Adobe PDF
|
2.15 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
