@inproceedings{hayakawa-etal-2022-jades,
title = "{JADES}: New Text Simplification Dataset in {J}apanese Targeted at Non-Native Speakers",
author = "Hayakawa, Akio and
Kajiwara, Tomoyuki and
Ouchi, Hiroki and
Watanabe, Taro",
editor = "{\v{S}}tajner, Sanja and
Saggion, Horacio and
Ferr{\'e}s, Daniel and
Shardlow, Matthew and
Sheang, Kim Cheng and
North, Kai and
Zampieri, Marcos and
Xu, Wei",
booktitle = "Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.tsar-1.17/",
doi = "10.18653/v1/2022.tsar-1.17",
pages = "179--187",
abstract = "The user-dependency of Text Simplification makes its evaluation obscure. A targeted evaluation dataset clarifies the purpose of simplification, though its specification is hard to define. We built JADES (JApanese Dataset for the Evaluation of Simplification), a text simplification dataset targeted at non-native Japanese speakers, according to public vocabulary and grammar profiles. JADES comprises 3,907 complex-simple sentence pairs annotated by an expert. Analysis of JADES shows that wide and multiple rewriting operations were applied through simplification. Furthermore, we analyzed outputs on JADES from several benchmark systems and automatic and manual scores of them. Results of these analyses highlight differences between English and Japanese in operations and evaluations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayakawa-etal-2022-jades">
<titleInfo>
<title>JADES: New Text Simplification Dataset in Japanese Targeted at Non-Native Speakers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akio</namePart>
<namePart type="family">Hayakawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Ferrés</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="given">Cheng</namePart>
<namePart type="family">Sheang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The user-dependency of Text Simplification makes its evaluation obscure. A targeted evaluation dataset clarifies the purpose of simplification, though its specification is hard to define. We built JADES (JApanese Dataset for the Evaluation of Simplification), a text simplification dataset targeted at non-native Japanese speakers, according to public vocabulary and grammar profiles. JADES comprises 3,907 complex-simple sentence pairs annotated by an expert. Analysis of JADES shows that wide and multiple rewriting operations were applied through simplification. Furthermore, we analyzed outputs on JADES from several benchmark systems and automatic and manual scores of them. Results of these analyses highlight differences between English and Japanese in operations and evaluations.</abstract>
<identifier type="citekey">hayakawa-etal-2022-jades</identifier>
<identifier type="doi">10.18653/v1/2022.tsar-1.17</identifier>
<location>
<url>https://aclanthology.org/2022.tsar-1.17/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>179</start>
<end>187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JADES: New Text Simplification Dataset in Japanese Targeted at Non-Native Speakers
%A Hayakawa, Akio
%A Kajiwara, Tomoyuki
%A Ouchi, Hiroki
%A Watanabe, Taro
%Y Štajner, Sanja
%Y Saggion, Horacio
%Y Ferrés, Daniel
%Y Shardlow, Matthew
%Y Sheang, Kim Cheng
%Y North, Kai
%Y Zampieri, Marcos
%Y Xu, Wei
%S Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Virtual)
%F hayakawa-etal-2022-jades
%X The user-dependency of Text Simplification makes its evaluation obscure. A targeted evaluation dataset clarifies the purpose of simplification, though its specification is hard to define. We built JADES (JApanese Dataset for the Evaluation of Simplification), a text simplification dataset targeted at non-native Japanese speakers, according to public vocabulary and grammar profiles. JADES comprises 3,907 complex-simple sentence pairs annotated by an expert. Analysis of JADES shows that wide and multiple rewriting operations were applied through simplification. Furthermore, we analyzed outputs on JADES from several benchmark systems and automatic and manual scores of them. Results of these analyses highlight differences between English and Japanese in operations and evaluations.
%R 10.18653/v1/2022.tsar-1.17
%U https://aclanthology.org/2022.tsar-1.17/
%U https://doi.org/10.18653/v1/2022.tsar-1.17
%P 179-187
Markdown (Informal)
[JADES: New Text Simplification Dataset in Japanese Targeted at Non-Native Speakers](https://aclanthology.org/2022.tsar-1.17/) (Hayakawa et al., TSAR 2022)
ACL