@inproceedings{sekine-etal-2022-resource,
title = "Resource of {W}ikipedias in 31 Languages Categorized into Fine-Grained Named Entities",
author = "Sekine, Satoshi and
Nakayama, Kouta and
Nomoto, Masako and
Ando, Maya and
Sumida, Asuka and
Matsuda, Koji",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.331",
pages = "3769--3777",
abstract = "This paper describes a resource of Wikipedias in 31 languages categorized into Extended Named Entity (ENE), which has 219 fine-grained NE categories. We first categorized 920 K Japanese Wikipedia pages according to the ENE scheme using machine learning, followed by manual validation. We then organized a shared task of Wikipedia categorization into 30 languages. The training data were provided by Japanese categorization and the language links, and the task was to categorize the Wikipedia pages into 30 languages, with no language links from Japanese Wikipedia (20M pages in total). Thirteen groups with 24 systems participated in the 2020 and 2021 tasks, sharing their outputs for resource-building. The Japanese categorization accuracy was 98.5{\%}, and the best performance among the 30 languages ranges from 80 to 93 in F-measure. Using ensemble learning, we created outputs with an average F-measure of 86.8, which is 1.7 better than the best single systems. The total size of the resource is 32.5M pages, including the training data. We call this resource creation scheme {``}Resource by Collaborative Contribution (RbCC){''}. We also constructed structuring tasks (attribute extraction and link prediction) using RbCC under our ongoing project, {``}SHINRA.{''}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sekine-etal-2022-resource">
<titleInfo>
<title>Resource of Wikipedias in 31 Languages Categorized into Fine-Grained Named Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sekine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kouta</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masako</namePart>
<namePart type="family">Nomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maya</namePart>
<namePart type="family">Ando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuka</namePart>
<namePart type="family">Sumida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Matsuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a resource of Wikipedias in 31 languages categorized into Extended Named Entity (ENE), which has 219 fine-grained NE categories. We first categorized 920 K Japanese Wikipedia pages according to the ENE scheme using machine learning, followed by manual validation. We then organized a shared task of Wikipedia categorization into 30 languages. The training data were provided by Japanese categorization and the language links, and the task was to categorize the Wikipedia pages into 30 languages, with no language links from Japanese Wikipedia (20M pages in total). Thirteen groups with 24 systems participated in the 2020 and 2021 tasks, sharing their outputs for resource-building. The Japanese categorization accuracy was 98.5%, and the best performance among the 30 languages ranges from 80 to 93 in F-measure. Using ensemble learning, we created outputs with an average F-measure of 86.8, which is 1.7 better than the best single systems. The total size of the resource is 32.5M pages, including the training data. We call this resource creation scheme “Resource by Collaborative Contribution (RbCC)”. We also constructed structuring tasks (attribute extraction and link prediction) using RbCC under our ongoing project, “SHINRA.”</abstract>
<identifier type="citekey">sekine-etal-2022-resource</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.331</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3769</start>
<end>3777</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resource of Wikipedias in 31 Languages Categorized into Fine-Grained Named Entities
%A Sekine, Satoshi
%A Nakayama, Kouta
%A Nomoto, Masako
%A Ando, Maya
%A Sumida, Asuka
%A Matsuda, Koji
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F sekine-etal-2022-resource
%X This paper describes a resource of Wikipedias in 31 languages categorized into Extended Named Entity (ENE), which has 219 fine-grained NE categories. We first categorized 920 K Japanese Wikipedia pages according to the ENE scheme using machine learning, followed by manual validation. We then organized a shared task of Wikipedia categorization into 30 languages. The training data were provided by Japanese categorization and the language links, and the task was to categorize the Wikipedia pages into 30 languages, with no language links from Japanese Wikipedia (20M pages in total). Thirteen groups with 24 systems participated in the 2020 and 2021 tasks, sharing their outputs for resource-building. The Japanese categorization accuracy was 98.5%, and the best performance among the 30 languages ranges from 80 to 93 in F-measure. Using ensemble learning, we created outputs with an average F-measure of 86.8, which is 1.7 better than the best single systems. The total size of the resource is 32.5M pages, including the training data. We call this resource creation scheme “Resource by Collaborative Contribution (RbCC)”. We also constructed structuring tasks (attribute extraction and link prediction) using RbCC under our ongoing project, “SHINRA.”
%U https://aclanthology.org/2022.coling-1.331
%P 3769-3777
Markdown (Informal)
[Resource of Wikipedias in 31 Languages Categorized into Fine-Grained Named Entities](https://aclanthology.org/2022.coling-1.331) (Sekine et al., COLING 2022)
ACL