@inproceedings{stengel-eskin-etal-2023-chicken,
title = "Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in {VQA}",
author = "Stengel-Eskin, Elias and
Guallar-Blasco, Jimena and
Zhou, Yi and
Van Durme, Benjamin",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.569",
doi = "10.18653/v1/2023.acl-long.569",
pages = "10220--10237",
abstract = "Natural language is ambiguous. Resolving ambiguous questions is key to successfully answering them. Focusing on questions about images, we create a dataset of ambiguous examples. We annotate these, grouping answers by the underlying question they address and rephrasing the question for each group to reduce ambiguity. Our analysis reveals a linguistically-aligned ontology of reasons for ambiguity in visual questions. We then develop an English question-generation model which we demonstrate via automatic and human evaluation produces less ambiguous questions. We further show that the question generation objective we use allows the model to integrate answer group information without any direct supervision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stengel-eskin-etal-2023-chicken">
<titleInfo>
<title>Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elias</namePart>
<namePart type="family">Stengel-Eskin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimena</namePart>
<namePart type="family">Guallar-Blasco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Van Durme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language is ambiguous. Resolving ambiguous questions is key to successfully answering them. Focusing on questions about images, we create a dataset of ambiguous examples. We annotate these, grouping answers by the underlying question they address and rephrasing the question for each group to reduce ambiguity. Our analysis reveals a linguistically-aligned ontology of reasons for ambiguity in visual questions. We then develop an English question-generation model which we demonstrate via automatic and human evaluation produces less ambiguous questions. We further show that the question generation objective we use allows the model to integrate answer group information without any direct supervision.</abstract>
<identifier type="citekey">stengel-eskin-etal-2023-chicken</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.569</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.569</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10220</start>
<end>10237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA
%A Stengel-Eskin, Elias
%A Guallar-Blasco, Jimena
%A Zhou, Yi
%A Van Durme, Benjamin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F stengel-eskin-etal-2023-chicken
%X Natural language is ambiguous. Resolving ambiguous questions is key to successfully answering them. Focusing on questions about images, we create a dataset of ambiguous examples. We annotate these, grouping answers by the underlying question they address and rephrasing the question for each group to reduce ambiguity. Our analysis reveals a linguistically-aligned ontology of reasons for ambiguity in visual questions. We then develop an English question-generation model which we demonstrate via automatic and human evaluation produces less ambiguous questions. We further show that the question generation objective we use allows the model to integrate answer group information without any direct supervision.
%R 10.18653/v1/2023.acl-long.569
%U https://aclanthology.org/2023.acl-long.569
%U https://doi.org/10.18653/v1/2023.acl-long.569
%P 10220-10237
Markdown (Informal)
[Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA](https://aclanthology.org/2023.acl-long.569) (Stengel-Eskin et al., ACL 2023)
ACL