@inproceedings{althani-etal-2024-using,
title = "Using In-context Learning to Automate {AI} Image Generation for a Gamified Text Labelling Task",
author = "Althani, Fatima and
Madge, Chris and
Poesio, Massimo",
editor = "Madge, Chris and
Chamberlain, Jon and
Fort, Karen and
Kruschwitz, Udo and
Lukin, Stephanie",
booktitle = "Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.games-1.4",
pages = "21--31",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="althani-etal-2024-using">
<titleInfo>
<title>Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatima</namePart>
<namePart type="family">Althani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Madge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Madge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Chamberlain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Fort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Kruschwitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Lukin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">althani-etal-2024-using</identifier>
<location>
<url>https://aclanthology.org/2024.games-1.4</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>21</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task
%A Althani, Fatima
%A Madge, Chris
%A Poesio, Massimo
%Y Madge, Chris
%Y Chamberlain, Jon
%Y Fort, Karen
%Y Kruschwitz, Udo
%Y Lukin, Stephanie
%S Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F althani-etal-2024-using
%X 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.
%U https://aclanthology.org/2024.games-1.4
%P 21-31
Markdown (Informal)
[Using In-context Learning to Automate AI Image Generation for a Gamified Text Labelling Task](https://aclanthology.org/2024.games-1.4) (Althani et al., games-WS 2024)
ACL