@inproceedings{britton-etal-2022-question,
title = "Question Modifiers in Visual Question Answering",
author = "Britton, William and
Sarkhel, Somdeb and
Venugopal, Deepak",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.158/",
pages = "1472--1479",
abstract = "Visual Question Answering (VQA) is a challenge problem that can advance AI by integrating several important sub-disciplines including natural language understanding and computer vision. Large VQA datasets that are publicly available for training and evaluation have driven the growth of VQA models that have obtained increasingly larger accuracy scores. However, it is also important to understand how much a model understands the details that are provided in a question. For example, studies in psychology have shown that syntactic complexity places a larger cognitive load on humans. Analogously, we want to understand if models have the perceptual capability to handle modifications to questions. Therefore, we develop a new dataset using Amazon Mechanical Turk where we asked workers to add modifiers to questions based on object properties and spatial relationships. We evaluate this data on LXMERT which is a state-of-the-art model in VQA that focuses more extensively on language processing. Our conclusions indicate that there is a significant negative impact on the performance of the model when the questions are modified to include more detailed information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="britton-etal-2022-question">
<titleInfo>
<title>Question Modifiers in Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Britton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Somdeb</namePart>
<namePart type="family">Sarkhel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Venugopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual Question Answering (VQA) is a challenge problem that can advance AI by integrating several important sub-disciplines including natural language understanding and computer vision. Large VQA datasets that are publicly available for training and evaluation have driven the growth of VQA models that have obtained increasingly larger accuracy scores. However, it is also important to understand how much a model understands the details that are provided in a question. For example, studies in psychology have shown that syntactic complexity places a larger cognitive load on humans. Analogously, we want to understand if models have the perceptual capability to handle modifications to questions. Therefore, we develop a new dataset using Amazon Mechanical Turk where we asked workers to add modifiers to questions based on object properties and spatial relationships. We evaluate this data on LXMERT which is a state-of-the-art model in VQA that focuses more extensively on language processing. Our conclusions indicate that there is a significant negative impact on the performance of the model when the questions are modified to include more detailed information.</abstract>
<identifier type="citekey">britton-etal-2022-question</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.158/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1472</start>
<end>1479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question Modifiers in Visual Question Answering
%A Britton, William
%A Sarkhel, Somdeb
%A Venugopal, Deepak
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F britton-etal-2022-question
%X Visual Question Answering (VQA) is a challenge problem that can advance AI by integrating several important sub-disciplines including natural language understanding and computer vision. Large VQA datasets that are publicly available for training and evaluation have driven the growth of VQA models that have obtained increasingly larger accuracy scores. However, it is also important to understand how much a model understands the details that are provided in a question. For example, studies in psychology have shown that syntactic complexity places a larger cognitive load on humans. Analogously, we want to understand if models have the perceptual capability to handle modifications to questions. Therefore, we develop a new dataset using Amazon Mechanical Turk where we asked workers to add modifiers to questions based on object properties and spatial relationships. We evaluate this data on LXMERT which is a state-of-the-art model in VQA that focuses more extensively on language processing. Our conclusions indicate that there is a significant negative impact on the performance of the model when the questions are modified to include more detailed information.
%U https://aclanthology.org/2022.lrec-1.158/
%P 1472-1479
Markdown (Informal)
[Question Modifiers in Visual Question Answering](https://aclanthology.org/2022.lrec-1.158/) (Britton et al., LREC 2022)
ACL
- William Britton, Somdeb Sarkhel, and Deepak Venugopal. 2022. Question Modifiers in Visual Question Answering. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1472–1479, Marseille, France. European Language Resources Association.