@inproceedings{kato-etal-2020-bert,
title = "{BERT}-Based Simplification of {J}apanese Sentence-Ending Predicates in Descriptive Text",
author = "Kato, Taichi and
Miyata, Rei and
Sato, Satoshi",
editor = "Davis, Brian and
Graham, Yvette and
Kelleher, John and
Sripada, Yaji",
booktitle = "Proceedings of the 13th International Conference on Natural Language Generation",
month = dec,
year = "2020",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.inlg-1.31",
doi = "10.18653/v1/2020.inlg-1.31",
pages = "242--251",
abstract = "Japanese sentence-ending predicates intricately combine content words and functional elements, such as aspect, modality, and honorifics; this can often hinder the understanding of language learners and children. Conventional lexical simplification methods, which replace difficult target words with simpler synonyms acquired from lexical resources in a word-by-word manner, are not always suitable for the simplification of such Japanese predicates. Given this situation, we propose a BERT-based simplification method, the core feature of which is the high ability to substitute the whole predicates with simple ones while maintaining their core meanings in the context by utilizing pre-trained masked language models. Experimental results showed that our proposed methods consistently outperformed the conventional thesaurus-based method by a wide margin. Furthermore, we investigated in detail the effectiveness of the average token embedding and dropout, and the remaining errors of our BERT-based methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kato-etal-2020-bert">
<titleInfo>
<title>BERT-Based Simplification of Japanese Sentence-Ending Predicates in Descriptive Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taichi</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rei</namePart>
<namePart type="family">Miyata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Davis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kelleher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Japanese sentence-ending predicates intricately combine content words and functional elements, such as aspect, modality, and honorifics; this can often hinder the understanding of language learners and children. Conventional lexical simplification methods, which replace difficult target words with simpler synonyms acquired from lexical resources in a word-by-word manner, are not always suitable for the simplification of such Japanese predicates. Given this situation, we propose a BERT-based simplification method, the core feature of which is the high ability to substitute the whole predicates with simple ones while maintaining their core meanings in the context by utilizing pre-trained masked language models. Experimental results showed that our proposed methods consistently outperformed the conventional thesaurus-based method by a wide margin. Furthermore, we investigated in detail the effectiveness of the average token embedding and dropout, and the remaining errors of our BERT-based methods.</abstract>
<identifier type="citekey">kato-etal-2020-bert</identifier>
<identifier type="doi">10.18653/v1/2020.inlg-1.31</identifier>
<location>
<url>https://aclanthology.org/2020.inlg-1.31</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>242</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT-Based Simplification of Japanese Sentence-Ending Predicates in Descriptive Text
%A Kato, Taichi
%A Miyata, Rei
%A Sato, Satoshi
%Y Davis, Brian
%Y Graham, Yvette
%Y Kelleher, John
%Y Sripada, Yaji
%S Proceedings of the 13th International Conference on Natural Language Generation
%D 2020
%8 December
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kato-etal-2020-bert
%X Japanese sentence-ending predicates intricately combine content words and functional elements, such as aspect, modality, and honorifics; this can often hinder the understanding of language learners and children. Conventional lexical simplification methods, which replace difficult target words with simpler synonyms acquired from lexical resources in a word-by-word manner, are not always suitable for the simplification of such Japanese predicates. Given this situation, we propose a BERT-based simplification method, the core feature of which is the high ability to substitute the whole predicates with simple ones while maintaining their core meanings in the context by utilizing pre-trained masked language models. Experimental results showed that our proposed methods consistently outperformed the conventional thesaurus-based method by a wide margin. Furthermore, we investigated in detail the effectiveness of the average token embedding and dropout, and the remaining errors of our BERT-based methods.
%R 10.18653/v1/2020.inlg-1.31
%U https://aclanthology.org/2020.inlg-1.31
%U https://doi.org/10.18653/v1/2020.inlg-1.31
%P 242-251
Markdown (Informal)
[BERT-Based Simplification of Japanese Sentence-Ending Predicates in Descriptive Text](https://aclanthology.org/2020.inlg-1.31) (Kato et al., INLG 2020)
ACL