@inproceedings{singh-etal-2021-mimoqa,
title = "{MIMOQA}: Multimodal Input Multimodal Output Question Answering",
author = "Singh, Hrituraj and
Nasery, Anshul and
Mehta, Denil and
Agarwal, Aishwarya and
Lamba, Jatin and
Srinivasan, Balaji Vasan",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.418",
doi = "10.18653/v1/2021.naacl-main.418",
pages = "5317--5332",
abstract = "Multimodal research has picked up significantly in the space of question answering with the task being extended to visual question answering, charts question answering as well as multimodal input question answering. However, all these explorations produce a unimodal textual output as the answer. In this paper, we propose a novel task - MIMOQA - Multimodal Input Multimodal Output Question Answering in which the output is also multimodal. Through human experiments, we empirically show that such multimodal outputs provide better cognitive understanding of the answers. We also propose a novel multimodal question-answering framework, MExBERT, that incorporates a joint textual and visual attention towards producing such a multimodal output. Our method relies on a novel multimodal dataset curated for this problem from publicly available unimodal datasets. We show the superior performance of MExBERT against strong baselines on both the automatic as well as human metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2021-mimoqa">
<titleInfo>
<title>MIMOQA: Multimodal Input Multimodal Output Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hrituraj</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anshul</namePart>
<namePart type="family">Nasery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denil</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Lamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balaji</namePart>
<namePart type="given">Vasan</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal research has picked up significantly in the space of question answering with the task being extended to visual question answering, charts question answering as well as multimodal input question answering. However, all these explorations produce a unimodal textual output as the answer. In this paper, we propose a novel task - MIMOQA - Multimodal Input Multimodal Output Question Answering in which the output is also multimodal. Through human experiments, we empirically show that such multimodal outputs provide better cognitive understanding of the answers. We also propose a novel multimodal question-answering framework, MExBERT, that incorporates a joint textual and visual attention towards producing such a multimodal output. Our method relies on a novel multimodal dataset curated for this problem from publicly available unimodal datasets. We show the superior performance of MExBERT against strong baselines on both the automatic as well as human metrics.</abstract>
<identifier type="citekey">singh-etal-2021-mimoqa</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.418</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.418</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5317</start>
<end>5332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIMOQA: Multimodal Input Multimodal Output Question Answering
%A Singh, Hrituraj
%A Nasery, Anshul
%A Mehta, Denil
%A Agarwal, Aishwarya
%A Lamba, Jatin
%A Srinivasan, Balaji Vasan
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F singh-etal-2021-mimoqa
%X Multimodal research has picked up significantly in the space of question answering with the task being extended to visual question answering, charts question answering as well as multimodal input question answering. However, all these explorations produce a unimodal textual output as the answer. In this paper, we propose a novel task - MIMOQA - Multimodal Input Multimodal Output Question Answering in which the output is also multimodal. Through human experiments, we empirically show that such multimodal outputs provide better cognitive understanding of the answers. We also propose a novel multimodal question-answering framework, MExBERT, that incorporates a joint textual and visual attention towards producing such a multimodal output. Our method relies on a novel multimodal dataset curated for this problem from publicly available unimodal datasets. We show the superior performance of MExBERT against strong baselines on both the automatic as well as human metrics.
%R 10.18653/v1/2021.naacl-main.418
%U https://aclanthology.org/2021.naacl-main.418
%U https://doi.org/10.18653/v1/2021.naacl-main.418
%P 5317-5332
Markdown (Informal)
[MIMOQA: Multimodal Input Multimodal Output Question Answering](https://aclanthology.org/2021.naacl-main.418) (Singh et al., NAACL 2021)
ACL
- Hrituraj Singh, Anshul Nasery, Denil Mehta, Aishwarya Agarwal, Jatin Lamba, and Balaji Vasan Srinivasan. 2021. MIMOQA: Multimodal Input Multimodal Output Question Answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5317–5332, Online. Association for Computational Linguistics.