@inproceedings{bi-etal-2025-dongbamie,
title = "{D}ongba{MIE}: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms",
author = "Bi, Xiaojun and
Li, Shuo and
Xing, Junyao and
Wang, Ziyue and
Luo, Fuwen and
Qiao, Weizheng and
Han, Lu and
Sun, Ziwei and
Li, Peng and
Liu, Yang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.51/",
pages = "976--990",
ISBN = "979-8-89176-335-7",
abstract = "Dongba pictographic is the only pictographic script still in use in the world. Its pictorial ideographic features carry rich cultural and contextual information. However, due to the lack of relevant datasets, research on semantic understanding of Dongba hieroglyphs has progressed slowly. To this end, we constructed DongbaMIE - the first dataset focusing on multimodal information extraction of Dongba pictographs. The dataset consists of images of Dongba hieroglyphic characters and their corresponding semantic annotations in Chinese. It contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs. The annotations cover four semantic dimensions: object, action, relation and attribute. Systematic evaluation of mainstream multimodal large language models shows that the models are difficult to perform information extraction of Dongba hieroglyphs efficiently under zero-shot and few-shot learning. Although supervised fine-tuning can improve the performance, accurate extraction of complex semantics is still a great challenge at present."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bi-etal-2025-dongbamie">
<titleInfo>
<title>DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyao</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuwen</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizheng</namePart>
<namePart type="family">Qiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Findings of the Association for Computational Linguistics: EMNLP 2025</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">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Dongba pictographic is the only pictographic script still in use in the world. Its pictorial ideographic features carry rich cultural and contextual information. However, due to the lack of relevant datasets, research on semantic understanding of Dongba hieroglyphs has progressed slowly. To this end, we constructed DongbaMIE - the first dataset focusing on multimodal information extraction of Dongba pictographs. The dataset consists of images of Dongba hieroglyphic characters and their corresponding semantic annotations in Chinese. It contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs. The annotations cover four semantic dimensions: object, action, relation and attribute. Systematic evaluation of mainstream multimodal large language models shows that the models are difficult to perform information extraction of Dongba hieroglyphs efficiently under zero-shot and few-shot learning. Although supervised fine-tuning can improve the performance, accurate extraction of complex semantics is still a great challenge at present.</abstract>
<identifier type="citekey">bi-etal-2025-dongbamie</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.51/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>976</start>
<end>990</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms
%A Bi, Xiaojun
%A Li, Shuo
%A Xing, Junyao
%A Wang, Ziyue
%A Luo, Fuwen
%A Qiao, Weizheng
%A Han, Lu
%A Sun, Ziwei
%A Li, Peng
%A Liu, Yang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F bi-etal-2025-dongbamie
%X Dongba pictographic is the only pictographic script still in use in the world. Its pictorial ideographic features carry rich cultural and contextual information. However, due to the lack of relevant datasets, research on semantic understanding of Dongba hieroglyphs has progressed slowly. To this end, we constructed DongbaMIE - the first dataset focusing on multimodal information extraction of Dongba pictographs. The dataset consists of images of Dongba hieroglyphic characters and their corresponding semantic annotations in Chinese. It contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs. The annotations cover four semantic dimensions: object, action, relation and attribute. Systematic evaluation of mainstream multimodal large language models shows that the models are difficult to perform information extraction of Dongba hieroglyphs efficiently under zero-shot and few-shot learning. Although supervised fine-tuning can improve the performance, accurate extraction of complex semantics is still a great challenge at present.
%U https://aclanthology.org/2025.findings-emnlp.51/
%P 976-990
Markdown (Informal)
[DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms](https://aclanthology.org/2025.findings-emnlp.51/) (Bi et al., Findings 2025)
ACL
- Xiaojun Bi, Shuo Li, Junyao Xing, Ziyue Wang, Fuwen Luo, Weizheng Qiao, Lu Han, Ziwei Sun, Peng Li, and Yang Liu. 2025. DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 976–990, Suzhou, China. Association for Computational Linguistics.