@inproceedings{nishihara-kajiwara-2020-word,
title = "Word Complexity Estimation for {J}apanese Lexical Simplification",
author = "Nishihara, Daiki and
Kajiwara, Tomoyuki",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.381",
pages = "3114--3120",
abstract = "We introduce three language resources for Japanese lexical simplification: 1) a large-scale word complexity lexicon, 2) the first synonym lexicon for converting complex words to simpler ones, and 3) the first toolkit for developing and benchmarking Japanese lexical simplification system. Our word complexity lexicon is expanded to a broader vocabulary using a classifier trained on a small, high-quality word complexity lexicon created by Japanese language teachers. Based on this word complexity estimator, we extracted simplified word pairs from a large-scale synonym lexicon and constructed a simplified synonym lexicon useful for lexical simplification. In addition, we developed a Python library that implements automatic evaluation and key methods in each subtask to ease the construction of a lexical simplification pipeline. Experimental results show that the proposed method based on our lexicon achieves the highest performance of Japanese lexical simplification. The current lexical simplification is mainly studied in English, which is rich in language resources such as lexicons and toolkits. The language resources constructed in this study will help advance the lexical simplification system in Japanese.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishihara-kajiwara-2020-word">
<titleInfo>
<title>Word Complexity Estimation for Japanese Lexical Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daiki</namePart>
<namePart type="family">Nishihara</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>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce three language resources for Japanese lexical simplification: 1) a large-scale word complexity lexicon, 2) the first synonym lexicon for converting complex words to simpler ones, and 3) the first toolkit for developing and benchmarking Japanese lexical simplification system. Our word complexity lexicon is expanded to a broader vocabulary using a classifier trained on a small, high-quality word complexity lexicon created by Japanese language teachers. Based on this word complexity estimator, we extracted simplified word pairs from a large-scale synonym lexicon and constructed a simplified synonym lexicon useful for lexical simplification. In addition, we developed a Python library that implements automatic evaluation and key methods in each subtask to ease the construction of a lexical simplification pipeline. Experimental results show that the proposed method based on our lexicon achieves the highest performance of Japanese lexical simplification. The current lexical simplification is mainly studied in English, which is rich in language resources such as lexicons and toolkits. The language resources constructed in this study will help advance the lexical simplification system in Japanese.</abstract>
<identifier type="citekey">nishihara-kajiwara-2020-word</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.381</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3114</start>
<end>3120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Complexity Estimation for Japanese Lexical Simplification
%A Nishihara, Daiki
%A Kajiwara, Tomoyuki
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F nishihara-kajiwara-2020-word
%X We introduce three language resources for Japanese lexical simplification: 1) a large-scale word complexity lexicon, 2) the first synonym lexicon for converting complex words to simpler ones, and 3) the first toolkit for developing and benchmarking Japanese lexical simplification system. Our word complexity lexicon is expanded to a broader vocabulary using a classifier trained on a small, high-quality word complexity lexicon created by Japanese language teachers. Based on this word complexity estimator, we extracted simplified word pairs from a large-scale synonym lexicon and constructed a simplified synonym lexicon useful for lexical simplification. In addition, we developed a Python library that implements automatic evaluation and key methods in each subtask to ease the construction of a lexical simplification pipeline. Experimental results show that the proposed method based on our lexicon achieves the highest performance of Japanese lexical simplification. The current lexical simplification is mainly studied in English, which is rich in language resources such as lexicons and toolkits. The language resources constructed in this study will help advance the lexical simplification system in Japanese.
%U https://aclanthology.org/2020.lrec-1.381
%P 3114-3120
Markdown (Informal)
[Word Complexity Estimation for Japanese Lexical Simplification](https://aclanthology.org/2020.lrec-1.381) (Nishihara & Kajiwara, LREC 2020)
ACL