@inproceedings{ramnath-etal-2021-worldly,
title = "Worldly Wise ({W}o{W}) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering",
author = "Ramnath, Kiran and
Sari, Leda and
Hasegawa-Johnson, Mark and
Yoo, Chang",
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.153",
doi = "10.18653/v1/2021.naacl-main.153",
pages = "1908--1919",
abstract = "Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we present a new task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA). FVSQA is based on the FVQA dataset, which requires a system to retrieve an entity from Knowledge Graphs (KGs) to answer a question about an image. In FVSQA, the question is spoken rather than typed. Three sub-tasks are proposed: (1) speech-to-text based, (2) end-to-end, without speech-to-text as an intermediate component, and (3) cross-lingual, in which the question is spoken in a language different from that in which the KG is recorded. The end-to-end and cross-lingual tasks are the first to require world knowledge from a multi-relational KG as a differentiable layer in an end-to-end spoken language understanding task, hence the proposed reference implementation is called Worldly-Wise (WoW).WoW is shown to perform end-to-end cross-lingual FVSQA at same levels of accuracy across 3 languages - English, Hindi, and Turkish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramnath-etal-2021-worldly">
<titleInfo>
<title>Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiran</namePart>
<namePart type="family">Ramnath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leda</namePart>
<namePart type="family">Sari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Hasegawa-Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Yoo</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>Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we present a new task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA). FVSQA is based on the FVQA dataset, which requires a system to retrieve an entity from Knowledge Graphs (KGs) to answer a question about an image. In FVSQA, the question is spoken rather than typed. Three sub-tasks are proposed: (1) speech-to-text based, (2) end-to-end, without speech-to-text as an intermediate component, and (3) cross-lingual, in which the question is spoken in a language different from that in which the KG is recorded. The end-to-end and cross-lingual tasks are the first to require world knowledge from a multi-relational KG as a differentiable layer in an end-to-end spoken language understanding task, hence the proposed reference implementation is called Worldly-Wise (WoW).WoW is shown to perform end-to-end cross-lingual FVSQA at same levels of accuracy across 3 languages - English, Hindi, and Turkish.</abstract>
<identifier type="citekey">ramnath-etal-2021-worldly</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.153</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.153</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1908</start>
<end>1919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering
%A Ramnath, Kiran
%A Sari, Leda
%A Hasegawa-Johnson, Mark
%A Yoo, Chang
%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 ramnath-etal-2021-worldly
%X Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we present a new task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA). FVSQA is based on the FVQA dataset, which requires a system to retrieve an entity from Knowledge Graphs (KGs) to answer a question about an image. In FVSQA, the question is spoken rather than typed. Three sub-tasks are proposed: (1) speech-to-text based, (2) end-to-end, without speech-to-text as an intermediate component, and (3) cross-lingual, in which the question is spoken in a language different from that in which the KG is recorded. The end-to-end and cross-lingual tasks are the first to require world knowledge from a multi-relational KG as a differentiable layer in an end-to-end spoken language understanding task, hence the proposed reference implementation is called Worldly-Wise (WoW).WoW is shown to perform end-to-end cross-lingual FVSQA at same levels of accuracy across 3 languages - English, Hindi, and Turkish.
%R 10.18653/v1/2021.naacl-main.153
%U https://aclanthology.org/2021.naacl-main.153
%U https://doi.org/10.18653/v1/2021.naacl-main.153
%P 1908-1919
Markdown (Informal)
[Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering](https://aclanthology.org/2021.naacl-main.153) (Ramnath et al., NAACL 2021)
ACL