Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task

Fatima Althani, Chris Madge, Massimo Poesio


Abstract
This paper explores a novel automated method to produce AI-generated images for a text-labelling gamified task. By leveraging the in-context learning capabilities of GPT-4, we automate the optimisation of text-to-image prompts to align with the text being labelled in the part-of-speech tagging task. As an initial evaluation, we compare the optimised prompts to the original sentences based on imageability and concreteness scores. Our results revealed that optimised prompts had significantly higher imageability and concreteness scores. Moreover, to evaluate text-to-image outputs, we generate images using Stable Diffusion XL based on the two prompt types, optimised prompts and the original sentences. Using the automated LIAON-Aesthetic predictor model, we assigned aesthetic scores for the generated images. This resulted in the outputs using optimised prompts scoring significantly higher in predicted aesthetics than those using original sentences as prompts. Our preliminary findings suggest that this methodology provides significantly more aesthetic text-to-image outputs than using the original sentence as a prompt. While the initial results are promising, the text labelling task and AI-generated images presented in this paper have yet to undergo human evaluation.
Anthology ID:
2024.games-1.4
Volume:
Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Chris Madge, Jon Chamberlain, Karen Fort, Udo Kruschwitz, Stephanie Lukin
Venues:
games | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
21–31
Language:
URL:
https://aclanthology.org/2024.games-1.4
DOI:
Bibkey:
Cite (ACL):
Fatima Althani, Chris Madge, and Massimo Poesio. 2024. Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task. In Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024, pages 21–31, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task (Althani et al., games-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.games-1.4.pdf