@inproceedings{khincha-etal-2023-infosync,
title = "{I}nfo{S}ync: Information Synchronization across Multilingual Semi-structured Tables",
author = "Khincha, Siddharth and
Jain, Chelsi and
Gupta, Vivek and
Kataria, Tushar and
Zhang, Shuo",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.159/",
doi = "10.18653/v1/2023.findings-acl.159",
pages = "2536--2559",
abstract = "Information Synchronization of semi-structured data across languages is challenging. For example, Wikipedia tables in one language need to be synchronized with others. To address this problem, we introduce a new dataset InfoSync and a two-step method for tabular synchronization. InfoSync contains 100K entity-centric tables (Wikipedia Infoboxes) across 14 languages, of which a subset ({\textasciitilde}3.5K pairs) are manually annotated. The proposed method includes 1) Information Alignment to map rows and 2) Information Update for updating missing/outdated information for aligned tables across multilingual tables. When evaluated on InfoSync, information alignment achieves an F1 score of 87.91 (en {\ensuremath{<}}-{\ensuremath{>}} non-en). To evaluate information updation, we perform human-assisted Wikipedia edits on Infoboxes for 532 table pairs. Our approach obtains an acceptance rate of 77.28{\%} on Wikipedia, showing the effectiveness of the proposed method."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khincha-etal-2023-infosync">
<titleInfo>
<title>InfoSync: Information Synchronization across Multilingual Semi-structured Tables</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Khincha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chelsi</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Kataria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Information Synchronization of semi-structured data across languages is challenging. For example, Wikipedia tables in one language need to be synchronized with others. To address this problem, we introduce a new dataset InfoSync and a two-step method for tabular synchronization. InfoSync contains 100K entity-centric tables (Wikipedia Infoboxes) across 14 languages, of which a subset (~3.5K pairs) are manually annotated. The proposed method includes 1) Information Alignment to map rows and 2) Information Update for updating missing/outdated information for aligned tables across multilingual tables. When evaluated on InfoSync, information alignment achieves an F1 score of 87.91 (en \ensuremath<-\ensuremath> non-en). To evaluate information updation, we perform human-assisted Wikipedia edits on Infoboxes for 532 table pairs. Our approach obtains an acceptance rate of 77.28% on Wikipedia, showing the effectiveness of the proposed method.</abstract>
<identifier type="citekey">khincha-etal-2023-infosync</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.159</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.159/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2536</start>
<end>2559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InfoSync: Information Synchronization across Multilingual Semi-structured Tables
%A Khincha, Siddharth
%A Jain, Chelsi
%A Gupta, Vivek
%A Kataria, Tushar
%A Zhang, Shuo
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F khincha-etal-2023-infosync
%X Information Synchronization of semi-structured data across languages is challenging. For example, Wikipedia tables in one language need to be synchronized with others. To address this problem, we introduce a new dataset InfoSync and a two-step method for tabular synchronization. InfoSync contains 100K entity-centric tables (Wikipedia Infoboxes) across 14 languages, of which a subset (~3.5K pairs) are manually annotated. The proposed method includes 1) Information Alignment to map rows and 2) Information Update for updating missing/outdated information for aligned tables across multilingual tables. When evaluated on InfoSync, information alignment achieves an F1 score of 87.91 (en \ensuremath<-\ensuremath> non-en). To evaluate information updation, we perform human-assisted Wikipedia edits on Infoboxes for 532 table pairs. Our approach obtains an acceptance rate of 77.28% on Wikipedia, showing the effectiveness of the proposed method.
%R 10.18653/v1/2023.findings-acl.159
%U https://aclanthology.org/2023.findings-acl.159/
%U https://doi.org/10.18653/v1/2023.findings-acl.159
%P 2536-2559
Markdown (Informal)
[InfoSync: Information Synchronization across Multilingual Semi-structured Tables](https://aclanthology.org/2023.findings-acl.159/) (Khincha et al., Findings 2023)
ACL