@inproceedings{tu-etal-2022-semeval,
title = "{S}em{E}val-2022 Task 9: {R}2{VQ} {--} Competence-based Multimodal Question Answering",
author = "Tu, Jingxuan and
Holderness, Eben and
Maru, Marco and
Conia, Simone and
Rim, Kyeongmin and
Lynch, Kelley and
Brutti, Richard and
Navigli, Roberto and
Pustejovsky, James",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.176",
doi = "10.18653/v1/2022.semeval-1.176",
pages = "1244--1255",
abstract = "In this task, we identify a challenge that is reflective of linguistic and cognitive competencies that humans have when speaking and reasoning. Particularly, given the intuition that textual and visual information mutually inform each other for semantic reasoning, we formulate a Competence-based Question Answering challenge, designed to involve rich semantic annotation and aligned text-video objects. The task is to answer questions from a collection of cooking recipes and videos, where each question belongs to a {``}question family{''} reflecting a specific reasoning competence. The data and task result is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2022-semeval">
<titleInfo>
<title>SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingxuan</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Maru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Conia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyeongmin</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelley</namePart>
<namePart type="family">Lynch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Brutti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</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>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</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>In this task, we identify a challenge that is reflective of linguistic and cognitive competencies that humans have when speaking and reasoning. Particularly, given the intuition that textual and visual information mutually inform each other for semantic reasoning, we formulate a Competence-based Question Answering challenge, designed to involve rich semantic annotation and aligned text-video objects. The task is to answer questions from a collection of cooking recipes and videos, where each question belongs to a “question family” reflecting a specific reasoning competence. The data and task result is publicly available.</abstract>
<identifier type="citekey">tu-etal-2022-semeval</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.176</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.176</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1244</start>
<end>1255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering
%A Tu, Jingxuan
%A Holderness, Eben
%A Maru, Marco
%A Conia, Simone
%A Rim, Kyeongmin
%A Lynch, Kelley
%A Brutti, Richard
%A Navigli, Roberto
%A Pustejovsky, James
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tu-etal-2022-semeval
%X In this task, we identify a challenge that is reflective of linguistic and cognitive competencies that humans have when speaking and reasoning. Particularly, given the intuition that textual and visual information mutually inform each other for semantic reasoning, we formulate a Competence-based Question Answering challenge, designed to involve rich semantic annotation and aligned text-video objects. The task is to answer questions from a collection of cooking recipes and videos, where each question belongs to a “question family” reflecting a specific reasoning competence. The data and task result is publicly available.
%R 10.18653/v1/2022.semeval-1.176
%U https://aclanthology.org/2022.semeval-1.176
%U https://doi.org/10.18653/v1/2022.semeval-1.176
%P 1244-1255
Markdown (Informal)
[SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering](https://aclanthology.org/2022.semeval-1.176) (Tu et al., SemEval 2022)
ACL
- Jingxuan Tu, Eben Holderness, Marco Maru, Simone Conia, Kyeongmin Rim, Kelley Lynch, Richard Brutti, Roberto Navigli, and James Pustejovsky. 2022. SemEval-2022 Task 9: R2VQ – Competence-based Multimodal Question Answering. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1244–1255, Seattle, United States. Association for Computational Linguistics.