@inproceedings{musacchio-etal-2026-madove,
title = "{M}a{DOVE}: a Dataset for Multilingual Document {VQA} Evaluation",
author = "Musacchio, Elio and
Siciliani, Lucia and
Basile, Pierpaolo and
Semeraro, Giovanni and
Zampedroni, Mark Federico and
Uboldi, Asia Beatrice",
editor = "T.Y.S.S., Santosh and
Agarwal, Amit and
Gupta, Vivek and
Kementchedjhieva, Yova and
Garimella, Aparna and
Hou, Yufang",
booktitle = "The Proceedings of Workshop on Document Intelligence and Understanding",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.docinsights-1.28/",
pages = "409--427",
ISBN = "979-8-89176-477-4",
abstract = "Visual Question Answering (VQA) is one of the most popular tasks in the fields of Computer Vision and Natural Language Processing. The task is to provide an answer to a question related to the contents of a given image. VQA has been expanded to several domains. One of these is document VQA, where the image is a page of a document and the question is related to the textual contents of the page. In this case, the system that is being evaluated has to understand textual contents that are written inside the image, differently from typical VQA where images are natural scenes. However, document VQA datasets are exclusively in English, hence the performance of the system is evaluated for the English language only. In light of this, we introduce MaDOVE (Multilingual DOcument VQA Evaluation), a novel dataset designed to evaluate document VQA in multiple languages. Moreover, to establish a strong benchmark, we conduct an extensive set of experiments by evaluating a diverse range of models on this task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="musacchio-etal-2026-madove">
<titleInfo>
<title>MaDOVE: a Dataset for Multilingual Document VQA Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elio</namePart>
<namePart type="family">Musacchio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Siciliani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierpaolo</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Semeraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="given">Federico</namePart>
<namePart type="family">Zampedroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asia</namePart>
<namePart type="given">Beatrice</namePart>
<namePart type="family">Uboldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of Workshop on Document Intelligence and Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-477-4</identifier>
</relatedItem>
<abstract>Visual Question Answering (VQA) is one of the most popular tasks in the fields of Computer Vision and Natural Language Processing. The task is to provide an answer to a question related to the contents of a given image. VQA has been expanded to several domains. One of these is document VQA, where the image is a page of a document and the question is related to the textual contents of the page. In this case, the system that is being evaluated has to understand textual contents that are written inside the image, differently from typical VQA where images are natural scenes. However, document VQA datasets are exclusively in English, hence the performance of the system is evaluated for the English language only. In light of this, we introduce MaDOVE (Multilingual DOcument VQA Evaluation), a novel dataset designed to evaluate document VQA in multiple languages. Moreover, to establish a strong benchmark, we conduct an extensive set of experiments by evaluating a diverse range of models on this task.</abstract>
<identifier type="citekey">musacchio-etal-2026-madove</identifier>
<location>
<url>https://aclanthology.org/2026.docinsights-1.28/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>409</start>
<end>427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaDOVE: a Dataset for Multilingual Document VQA Evaluation
%A Musacchio, Elio
%A Siciliani, Lucia
%A Basile, Pierpaolo
%A Semeraro, Giovanni
%A Zampedroni, Mark Federico
%A Uboldi, Asia Beatrice
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F musacchio-etal-2026-madove
%X Visual Question Answering (VQA) is one of the most popular tasks in the fields of Computer Vision and Natural Language Processing. The task is to provide an answer to a question related to the contents of a given image. VQA has been expanded to several domains. One of these is document VQA, where the image is a page of a document and the question is related to the textual contents of the page. In this case, the system that is being evaluated has to understand textual contents that are written inside the image, differently from typical VQA where images are natural scenes. However, document VQA datasets are exclusively in English, hence the performance of the system is evaluated for the English language only. In light of this, we introduce MaDOVE (Multilingual DOcument VQA Evaluation), a novel dataset designed to evaluate document VQA in multiple languages. Moreover, to establish a strong benchmark, we conduct an extensive set of experiments by evaluating a diverse range of models on this task.
%U https://aclanthology.org/2026.docinsights-1.28/
%P 409-427
Markdown (Informal)
[MaDOVE: a Dataset for Multilingual Document VQA Evaluation](https://aclanthology.org/2026.docinsights-1.28/) (Musacchio et al., DocInsights 2026)
ACL
- Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Giovanni Semeraro, Mark Federico Zampedroni, and Asia Beatrice Uboldi. 2026. MaDOVE: a Dataset for Multilingual Document VQA Evaluation. In The Proceedings of Workshop on Document Intelligence and Understanding, pages 409–427, Budapest, Hungary. Association for Computational Linguistics.