@inproceedings{li-sogaard-2022-qlevr,
title = "{QLEVR}: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning",
author = "Li, Zechen and
S{\o}gaard, Anders",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.73",
doi = "10.18653/v1/2022.findings-naacl.73",
pages = "980--996",
abstract = "Synthetic datasets have successfully been used to probe visual question-answering datasets for their reasoning abilities. CLEVR (John- son et al., 2017), for example, tests a range of visual reasoning abilities. The questions in CLEVR focus on comparisons of shapes, colors, and sizes, numerical reasoning, and existence claims. This paper introduces a minimally biased, diagnostic visual question-answering dataset, QLEVR, that goes beyond existential and numerical quantification and focus on more complex quantifiers and their combinations, e.g., asking whether there are more than two red balls that are smaller than at least three blue balls in an image. We describe how the dataset was created and present a first evaluation of state-of-the-art visual question-answering models, showing that QLEVR presents a formidable challenge to our current models. Code and Dataset are available at \url{https://github.com/zechenli03/QLEVR}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-sogaard-2022-qlevr">
<titleInfo>
<title>QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zechen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Synthetic datasets have successfully been used to probe visual question-answering datasets for their reasoning abilities. CLEVR (John- son et al., 2017), for example, tests a range of visual reasoning abilities. The questions in CLEVR focus on comparisons of shapes, colors, and sizes, numerical reasoning, and existence claims. This paper introduces a minimally biased, diagnostic visual question-answering dataset, QLEVR, that goes beyond existential and numerical quantification and focus on more complex quantifiers and their combinations, e.g., asking whether there are more than two red balls that are smaller than at least three blue balls in an image. We describe how the dataset was created and present a first evaluation of state-of-the-art visual question-answering models, showing that QLEVR presents a formidable challenge to our current models. Code and Dataset are available at https://github.com/zechenli03/QLEVR</abstract>
<identifier type="citekey">li-sogaard-2022-qlevr</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.73</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.73</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>980</start>
<end>996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning
%A Li, Zechen
%A Søgaard, Anders
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F li-sogaard-2022-qlevr
%X Synthetic datasets have successfully been used to probe visual question-answering datasets for their reasoning abilities. CLEVR (John- son et al., 2017), for example, tests a range of visual reasoning abilities. The questions in CLEVR focus on comparisons of shapes, colors, and sizes, numerical reasoning, and existence claims. This paper introduces a minimally biased, diagnostic visual question-answering dataset, QLEVR, that goes beyond existential and numerical quantification and focus on more complex quantifiers and their combinations, e.g., asking whether there are more than two red balls that are smaller than at least three blue balls in an image. We describe how the dataset was created and present a first evaluation of state-of-the-art visual question-answering models, showing that QLEVR presents a formidable challenge to our current models. Code and Dataset are available at https://github.com/zechenli03/QLEVR
%R 10.18653/v1/2022.findings-naacl.73
%U https://aclanthology.org/2022.findings-naacl.73
%U https://doi.org/10.18653/v1/2022.findings-naacl.73
%P 980-996
Markdown (Informal)
[QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning](https://aclanthology.org/2022.findings-naacl.73) (Li & Søgaard, Findings 2022)
ACL