@inproceedings{chen-etal-2024-textlap,
title = "{T}ext{L}ap: Customizing Language Models for Text-to-Layout Planning",
author = "Chen, Jian and
Zhang, Ruiyi and
Zhou, Yufan and
Healey, Jennifer and
Gu, Jiuxiang and
Xu, Zhiqiang and
Chen, Changyou",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.833/",
doi = "10.18653/v1/2024.findings-emnlp.833",
pages = "14275--14289",
abstract = "Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. Human annotators are asked to build a benchmark to evaluate different layout planning models. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for document generation and graphical design benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-textlap">
<titleInfo>
<title>TextLap: Customizing Language Models for Text-to-Layout Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Healey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiuxiang</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changyou</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. Human annotators are asked to build a benchmark to evaluate different layout planning models. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for document generation and graphical design benchmarks.</abstract>
<identifier type="citekey">chen-etal-2024-textlap</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.833</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.833/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>14275</start>
<end>14289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TextLap: Customizing Language Models for Text-to-Layout Planning
%A Chen, Jian
%A Zhang, Ruiyi
%A Zhou, Yufan
%A Healey, Jennifer
%A Gu, Jiuxiang
%A Xu, Zhiqiang
%A Chen, Changyou
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F chen-etal-2024-textlap
%X Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. Human annotators are asked to build a benchmark to evaluate different layout planning models. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for document generation and graphical design benchmarks.
%R 10.18653/v1/2024.findings-emnlp.833
%U https://aclanthology.org/2024.findings-emnlp.833/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.833
%P 14275-14289
Markdown (Informal)
[TextLap: Customizing Language Models for Text-to-Layout Planning](https://aclanthology.org/2024.findings-emnlp.833/) (Chen et al., Findings 2024)
ACL
- Jian Chen, Ruiyi Zhang, Yufan Zhou, Jennifer Healey, Jiuxiang Gu, Zhiqiang Xu, and Changyou Chen. 2024. TextLap: Customizing Language Models for Text-to-Layout Planning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14275–14289, Miami, Florida, USA. Association for Computational Linguistics.