@inproceedings{thierauf-etal-2024-automating-dataset,
title = "Automating Dataset Production Using Generative Text and Image Models",
author = "Thierauf, Christopher and
Abrams, Mitchell and
Scheutz, Matthias",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.179",
pages = "1988--1995",
abstract = "Practical and ethical dataset collection remains a challenge blocking many empirical methods in natural language processing, resulting in a lack of benchmarks or data on which to test hypotheses. We propose a solution to some of these areas by presenting a pipeline to reduce the research burden of producing image and text datasets when datasets may not exist. Our approach, with accompanying software tools, involves (1) generating text with LLMs; (2) creating accompanying image vignettes with text{--}to{--}image transformers; and (3) low-cost human validation. Based on existing literature that has struggled with quantitative evaluation (due to difficulty of data collection), we present the creation of 3 relevant datasets, and conduct a user study that demonstrates this approach is able to aid researchers in obtaining previously-challenging datasets. We provide sample data generated with this technique, the source code used to produce it, and discuss applicability and limitations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thierauf-etal-2024-automating-dataset">
<titleInfo>
<title>Automating Dataset Production Using Generative Text and Image Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Thierauf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitchell</namePart>
<namePart type="family">Abrams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Scheutz</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>Practical and ethical dataset collection remains a challenge blocking many empirical methods in natural language processing, resulting in a lack of benchmarks or data on which to test hypotheses. We propose a solution to some of these areas by presenting a pipeline to reduce the research burden of producing image and text datasets when datasets may not exist. Our approach, with accompanying software tools, involves (1) generating text with LLMs; (2) creating accompanying image vignettes with text–to–image transformers; and (3) low-cost human validation. Based on existing literature that has struggled with quantitative evaluation (due to difficulty of data collection), we present the creation of 3 relevant datasets, and conduct a user study that demonstrates this approach is able to aid researchers in obtaining previously-challenging datasets. We provide sample data generated with this technique, the source code used to produce it, and discuss applicability and limitations.</abstract>
<identifier type="citekey">thierauf-etal-2024-automating-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.179</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1988</start>
<end>1995</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automating Dataset Production Using Generative Text and Image Models
%A Thierauf, Christopher
%A Abrams, Mitchell
%A Scheutz, Matthias
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F thierauf-etal-2024-automating-dataset
%X Practical and ethical dataset collection remains a challenge blocking many empirical methods in natural language processing, resulting in a lack of benchmarks or data on which to test hypotheses. We propose a solution to some of these areas by presenting a pipeline to reduce the research burden of producing image and text datasets when datasets may not exist. Our approach, with accompanying software tools, involves (1) generating text with LLMs; (2) creating accompanying image vignettes with text–to–image transformers; and (3) low-cost human validation. Based on existing literature that has struggled with quantitative evaluation (due to difficulty of data collection), we present the creation of 3 relevant datasets, and conduct a user study that demonstrates this approach is able to aid researchers in obtaining previously-challenging datasets. We provide sample data generated with this technique, the source code used to produce it, and discuss applicability and limitations.
%U https://aclanthology.org/2024.lrec-main.179
%P 1988-1995
Markdown (Informal)
[Automating Dataset Production Using Generative Text and Image Models](https://aclanthology.org/2024.lrec-main.179) (Thierauf et al., LREC-COLING 2024)
ACL