Thanks to independent advances in language and image generation we could soon be in the position to have systems that communicate with humans by combining language and images in their output, a skill that humans do not possess (we receive, but do not produce images at high speed). The paper explores some of the implications of this idea: which kinds of data sets need to be developed to train such systems, in which cases language and images could be most usefully integrated and which issues could arise on the image generation and language+image integration side.
One Picture and a Thousand Words: Generative Language+images Models and How to Train Them / Zamparelli, R.. - ELETTRONICO. - 3551:(2023). (Intervento presentato al convegno 7th Workshop on Natural Language for Artificial Intelligence, NL4AI 2023 tenutosi a Roma nel 6 novembre-7 novembre 2023).
One Picture and a Thousand Words: Generative Language+images Models and How to Train Them
Zamparelli R.
2023-01-01
Abstract
Thanks to independent advances in language and image generation we could soon be in the position to have systems that communicate with humans by combining language and images in their output, a skill that humans do not possess (we receive, but do not produce images at high speed). The paper explores some of the implications of this idea: which kinds of data sets need to be developed to train such systems, in which cases language and images could be most usefully integrated and which issues could arise on the image generation and language+image integration side.| File | Dimensione | Formato | |
|---|---|---|---|
|
paper11.pdf
accesso aperto
Descrizione: One Picture and a Thousand Words Generative Language+images Models and How to Train Them
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
1.4 MB
Formato
Adobe PDF
|
1.4 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
