@inproceedings{akter-etal-2024-visreas,
title = "{VISREAS}: Complex Visual Reasoning with Unanswerable Questions",
author = "Akter, Syeda Nahida and
Lee, Sangwu and
Chang, Yingshan and
Bisk, Yonatan and
Nyberg, Eric",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.402",
pages = "6735--6752",
abstract = "Verifying a question{'}s validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the users rather than generating the best possible answer. Addressing this requirement, we introduce a new compositional visual question-answering dataset, VisReas, that consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. VisReas contains 2.07M semantically diverse queries generated automatically using Visual Genome scene graphs. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, Logic2Vision that reasons by producing and executing pseudocode without any external modules to generate the answer. Logic2Vision outperforms generative models in VisReas (+4.82{\%} over LLaVA-1.5; +12.23{\%} over InstructBLIP) and achieves a significant gain in performance against the classification models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akter-etal-2024-visreas">
<titleInfo>
<title>VISREAS: Complex Visual Reasoning with Unanswerable Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syeda</namePart>
<namePart type="given">Nahida</namePart>
<namePart type="family">Akter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangwu</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingshan</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Bisk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Nyberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Verifying a question’s validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the users rather than generating the best possible answer. Addressing this requirement, we introduce a new compositional visual question-answering dataset, VisReas, that consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. VisReas contains 2.07M semantically diverse queries generated automatically using Visual Genome scene graphs. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, Logic2Vision that reasons by producing and executing pseudocode without any external modules to generate the answer. Logic2Vision outperforms generative models in VisReas (+4.82% over LLaVA-1.5; +12.23% over InstructBLIP) and achieves a significant gain in performance against the classification models.</abstract>
<identifier type="citekey">akter-etal-2024-visreas</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.402</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6735</start>
<end>6752</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VISREAS: Complex Visual Reasoning with Unanswerable Questions
%A Akter, Syeda Nahida
%A Lee, Sangwu
%A Chang, Yingshan
%A Bisk, Yonatan
%A Nyberg, Eric
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F akter-etal-2024-visreas
%X Verifying a question’s validity before answering is crucial in real-world applications, where users may provide imperfect instructions. In this scenario, an ideal model should address the discrepancies in the query and convey them to the users rather than generating the best possible answer. Addressing this requirement, we introduce a new compositional visual question-answering dataset, VisReas, that consists of answerable and unanswerable visual queries formulated by traversing and perturbing commonalities and differences among objects, attributes, and relations. VisReas contains 2.07M semantically diverse queries generated automatically using Visual Genome scene graphs. The unique feature of this task, validating question answerability with respect to an image before answering, and the poor performance of state-of-the-art models inspired the design of a new modular baseline, Logic2Vision that reasons by producing and executing pseudocode without any external modules to generate the answer. Logic2Vision outperforms generative models in VisReas (+4.82% over LLaVA-1.5; +12.23% over InstructBLIP) and achieves a significant gain in performance against the classification models.
%U https://aclanthology.org/2024.findings-acl.402
%P 6735-6752
Markdown (Informal)
[VISREAS: Complex Visual Reasoning with Unanswerable Questions](https://aclanthology.org/2024.findings-acl.402) (Akter et al., Findings 2024)
ACL
- Syeda Nahida Akter, Sangwu Lee, Yingshan Chang, Yonatan Bisk, and Eric Nyberg. 2024. VISREAS: Complex Visual Reasoning with Unanswerable Questions. In Findings of the Association for Computational Linguistics ACL 2024, pages 6735–6752, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.