@inproceedings{hassan-etal-2026-digilians-imageeval,
title = "Digilians at {I}mage{E}val 2026 Shared Tasks: Modular Speech Parsing and Joint Multimodal Reasoning for {A}rabic Spoken {VQA}",
author = "Hassan, Ahmed Eid and
Hossam, Nour Eldeen and
Rashad, Ahmed Hossam and
Fawzy, Abdelrhman Mahmoud and
Abdelmeguid, Mohammed Eid and
Mohamed, Mohamed Hamdy",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.96/",
pages = "766--770",
ISBN = "979-8-89176-497-2",
abstract = "We describe the Digilians submission to Task 1a (Spoken Visual Question Answering, MSA track) of the ImageEval 2026 shared task (Abdaljalil et al., 2026). Our system splits the problem into independently cacheable stages: speech recognition, schema-constrained transcript parsing that recovers a question and three candidate answers from continuous Arabic speech, a conditional repair mechanism that escalates to a larger ASR model only for semantically degenerate parses, and a joint multiplechoice visual reasoning stage that evaluates all three candidates against the image simultaneously rather than scoring them independently. On the labeled development split (500 records, synthetic voice-cloned audio), our production configuration reaches 79.0{\%} accuracy against a 39.8{\%} official baseline, with nearly the entire gain over an earlier configuration coming from a single change to the answer-selection model. On the blind final test split (1,000 records, human-recorded audio), the same frozen configuration scores 65.6{\%} accuracy / 57.4{\%} balanced accuracy / 50.4{\%} macro F1, a substantial drop we attribute to the dev-to-test recordingcondition shift and report as our most important finding. We also surface a caching-related reproducibility issue uncovered during development and discuss what both findings imply for pipelines built the same way."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hassan-etal-2026-digilians-imageeval">
<titleInfo>
<title>Digilians at ImageEval 2026 Shared Tasks: Modular Speech Parsing and Joint Multimodal Reasoning for Arabic Spoken VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Eid</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nour</namePart>
<namePart type="given">Eldeen</namePart>
<namePart type="family">Hossam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Hossam</namePart>
<namePart type="family">Rashad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrhman</namePart>
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Fawzy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Eid</namePart>
<namePart type="family">Abdelmeguid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mohamed</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>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>We describe the Digilians submission to Task 1a (Spoken Visual Question Answering, MSA track) of the ImageEval 2026 shared task (Abdaljalil et al., 2026). Our system splits the problem into independently cacheable stages: speech recognition, schema-constrained transcript parsing that recovers a question and three candidate answers from continuous Arabic speech, a conditional repair mechanism that escalates to a larger ASR model only for semantically degenerate parses, and a joint multiplechoice visual reasoning stage that evaluates all three candidates against the image simultaneously rather than scoring them independently. On the labeled development split (500 records, synthetic voice-cloned audio), our production configuration reaches 79.0% accuracy against a 39.8% official baseline, with nearly the entire gain over an earlier configuration coming from a single change to the answer-selection model. On the blind final test split (1,000 records, human-recorded audio), the same frozen configuration scores 65.6% accuracy / 57.4% balanced accuracy / 50.4% macro F1, a substantial drop we attribute to the dev-to-test recordingcondition shift and report as our most important finding. We also surface a caching-related reproducibility issue uncovered during development and discuss what both findings imply for pipelines built the same way.</abstract>
<identifier type="citekey">hassan-etal-2026-digilians-imageeval</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.96/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>766</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Digilians at ImageEval 2026 Shared Tasks: Modular Speech Parsing and Joint Multimodal Reasoning for Arabic Spoken VQA
%A Hassan, Ahmed Eid
%A Hossam, Nour Eldeen
%A Rashad, Ahmed Hossam
%A Fawzy, Abdelrhman Mahmoud
%A Abdelmeguid, Mohammed Eid
%A Mohamed, Mohamed Hamdy
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F hassan-etal-2026-digilians-imageeval
%X We describe the Digilians submission to Task 1a (Spoken Visual Question Answering, MSA track) of the ImageEval 2026 shared task (Abdaljalil et al., 2026). Our system splits the problem into independently cacheable stages: speech recognition, schema-constrained transcript parsing that recovers a question and three candidate answers from continuous Arabic speech, a conditional repair mechanism that escalates to a larger ASR model only for semantically degenerate parses, and a joint multiplechoice visual reasoning stage that evaluates all three candidates against the image simultaneously rather than scoring them independently. On the labeled development split (500 records, synthetic voice-cloned audio), our production configuration reaches 79.0% accuracy against a 39.8% official baseline, with nearly the entire gain over an earlier configuration coming from a single change to the answer-selection model. On the blind final test split (1,000 records, human-recorded audio), the same frozen configuration scores 65.6% accuracy / 57.4% balanced accuracy / 50.4% macro F1, a substantial drop we attribute to the dev-to-test recordingcondition shift and report as our most important finding. We also surface a caching-related reproducibility issue uncovered during development and discuss what both findings imply for pipelines built the same way.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.96/
%P 766-770
Markdown (Informal)
[Digilians at ImageEval 2026 Shared Tasks: Modular Speech Parsing and Joint Multimodal Reasoning for Arabic Spoken VQA](https://aclanthology.org/2026.arabicnlp-sharedtasks.96/) (Hassan et al., ArabicNLP 2026)
ACL