@inproceedings{niu-etal-2025-chart2code53,
title = "{C}hart2{C}ode53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation",
author = "Niu, Tianhao and
Cui, Yiming and
Wang, Baoxin and
Xu, Xiao and
Yao, Xin and
Zhu, Qingfu and
Wu, Dayong and
Wang, Shijin and
Che, Wanxiang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.799/",
pages = "15839--15855",
ISBN = "979-8-89176-332-6",
abstract = "Chart2code has recently received significant attention in the multimodal community due to its potential to reduce the burden of visualization and promote a more detailed understanding of charts. However, existing Chart2code-related training datasets suffer from at least one of the following issues: (1) limited scale, (2) limited type coverage, and (3) inadequate complexity. To address these challenges, we seek more diverse sources that better align with real-world user distributions and propose dual data synthesis pipelines: (1) synthesize based on online plotting code. (2) synthesize based on chart images in the academic paper. We create a large-scale Chart2code training dataset Chart2code53, including 53 chart types, 130K Chart-code pairs based on the pipeline. Experimental results demonstrate that even with few parameters, the model finetuned on Chart2code53 achieves state-of-the-art performance on multiple Chart2code benchmarks within open-source models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niu-etal-2025-chart2code53">
<titleInfo>
<title>Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianhao</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingfu</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Chart2code has recently received significant attention in the multimodal community due to its potential to reduce the burden of visualization and promote a more detailed understanding of charts. However, existing Chart2code-related training datasets suffer from at least one of the following issues: (1) limited scale, (2) limited type coverage, and (3) inadequate complexity. To address these challenges, we seek more diverse sources that better align with real-world user distributions and propose dual data synthesis pipelines: (1) synthesize based on online plotting code. (2) synthesize based on chart images in the academic paper. We create a large-scale Chart2code training dataset Chart2code53, including 53 chart types, 130K Chart-code pairs based on the pipeline. Experimental results demonstrate that even with few parameters, the model finetuned on Chart2code53 achieves state-of-the-art performance on multiple Chart2code benchmarks within open-source models.</abstract>
<identifier type="citekey">niu-etal-2025-chart2code53</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.799/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15839</start>
<end>15855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation
%A Niu, Tianhao
%A Cui, Yiming
%A Wang, Baoxin
%A Xu, Xiao
%A Yao, Xin
%A Zhu, Qingfu
%A Wu, Dayong
%A Wang, Shijin
%A Che, Wanxiang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F niu-etal-2025-chart2code53
%X Chart2code has recently received significant attention in the multimodal community due to its potential to reduce the burden of visualization and promote a more detailed understanding of charts. However, existing Chart2code-related training datasets suffer from at least one of the following issues: (1) limited scale, (2) limited type coverage, and (3) inadequate complexity. To address these challenges, we seek more diverse sources that better align with real-world user distributions and propose dual data synthesis pipelines: (1) synthesize based on online plotting code. (2) synthesize based on chart images in the academic paper. We create a large-scale Chart2code training dataset Chart2code53, including 53 chart types, 130K Chart-code pairs based on the pipeline. Experimental results demonstrate that even with few parameters, the model finetuned on Chart2code53 achieves state-of-the-art performance on multiple Chart2code benchmarks within open-source models.
%U https://aclanthology.org/2025.emnlp-main.799/
%P 15839-15855
Markdown (Informal)
[Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation](https://aclanthology.org/2025.emnlp-main.799/) (Niu et al., EMNLP 2025)
ACL
- Tianhao Niu, Yiming Cui, Baoxin Wang, Xiao Xu, Xin Yao, Qingfu Zhu, Dayong Wu, Shijin Wang, and Wanxiang Che. 2025. Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 15839–15855, Suzhou, China. Association for Computational Linguistics.