@inproceedings{parida-etal-2025-ovqa,
title = "{OVQA}: A Dataset for Visual Question Answering and Multimodal Research in {O}dia Language",
author = "Parida, Shantipriya and
Sahoo, Shashikanta and
Sekhar, Sambit and
Sahoo, Kalyanamalini and
Kotwal, Ketan and
Khosla, Sonal and
Dash, Satya Ranjan and
Bose, Aneesh and
Kohli, Guneet Singh and
Lenka, Smruti Smita and
Bojar, Ond{\v{r}}ej",
editor = "Weerasinghe, Ruvan and
Anuradha, Isuri and
Sumanathilaka, Deshan",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages",
month = jan,
year = "2025",
address = "Abu Dhabi",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.indonlp-1.7/",
pages = "58--66",
abstract = "This paper introduces OVQA, the first multimodal dataset designed for visual question-answering (VQA), visual question elicitation (VQE), and multimodal research for the low-resource Odia language. The dataset was created by manually translating 6,149 English question-answer pairs, each associated with 6,149 unique images from the Visual Genome dataset. This effort resulted in 27,809 English-Odia parallel sentences, ensuring a semantic match with the corresponding visual information. Several baseline experiments were conducted on the dataset, including visual question answering and visual question elicitation. The dataset is the first VQA dataset for the low-resource Odia language and will be released for multimodal research purposes and also help researchers extend for other low-resource languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parida-etal-2025-ovqa">
<titleInfo>
<title>OVQA: A Dataset for Visual Question Answering and Multimodal Research in Odia Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashikanta</namePart>
<namePart type="family">Sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sambit</namePart>
<namePart type="family">Sekhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyanamalini</namePart>
<namePart type="family">Sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ketan</namePart>
<namePart type="family">Kotwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonal</namePart>
<namePart type="family">Khosla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aneesh</namePart>
<namePart type="family">Bose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guneet</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Kohli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smruti</namePart>
<namePart type="given">Smita</namePart>
<namePart type="family">Lenka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruvan</namePart>
<namePart type="family">Weerasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="family">Anuradha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deshan</namePart>
<namePart type="family">Sumanathilaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces OVQA, the first multimodal dataset designed for visual question-answering (VQA), visual question elicitation (VQE), and multimodal research for the low-resource Odia language. The dataset was created by manually translating 6,149 English question-answer pairs, each associated with 6,149 unique images from the Visual Genome dataset. This effort resulted in 27,809 English-Odia parallel sentences, ensuring a semantic match with the corresponding visual information. Several baseline experiments were conducted on the dataset, including visual question answering and visual question elicitation. The dataset is the first VQA dataset for the low-resource Odia language and will be released for multimodal research purposes and also help researchers extend for other low-resource languages.</abstract>
<identifier type="citekey">parida-etal-2025-ovqa</identifier>
<location>
<url>https://aclanthology.org/2025.indonlp-1.7/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>58</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OVQA: A Dataset for Visual Question Answering and Multimodal Research in Odia Language
%A Parida, Shantipriya
%A Sahoo, Shashikanta
%A Sekhar, Sambit
%A Sahoo, Kalyanamalini
%A Kotwal, Ketan
%A Khosla, Sonal
%A Dash, Satya Ranjan
%A Bose, Aneesh
%A Kohli, Guneet Singh
%A Lenka, Smruti Smita
%A Bojar, Ondřej
%Y Weerasinghe, Ruvan
%Y Anuradha, Isuri
%Y Sumanathilaka, Deshan
%S Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi
%F parida-etal-2025-ovqa
%X This paper introduces OVQA, the first multimodal dataset designed for visual question-answering (VQA), visual question elicitation (VQE), and multimodal research for the low-resource Odia language. The dataset was created by manually translating 6,149 English question-answer pairs, each associated with 6,149 unique images from the Visual Genome dataset. This effort resulted in 27,809 English-Odia parallel sentences, ensuring a semantic match with the corresponding visual information. Several baseline experiments were conducted on the dataset, including visual question answering and visual question elicitation. The dataset is the first VQA dataset for the low-resource Odia language and will be released for multimodal research purposes and also help researchers extend for other low-resource languages.
%U https://aclanthology.org/2025.indonlp-1.7/
%P 58-66
Markdown (Informal)
[OVQA: A Dataset for Visual Question Answering and Multimodal Research in Odia Language](https://aclanthology.org/2025.indonlp-1.7/) (Parida et al., IndoNLP 2025)
ACL
- Shantipriya Parida, Shashikanta Sahoo, Sambit Sekhar, Kalyanamalini Sahoo, Ketan Kotwal, Sonal Khosla, Satya Ranjan Dash, Aneesh Bose, Guneet Singh Kohli, Smruti Smita Lenka, and Ondřej Bojar. 2025. OVQA: A Dataset for Visual Question Answering and Multimodal Research in Odia Language. In Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages, pages 58–66, Abu Dhabi. Association for Computational Linguistics.