@inproceedings{kim-etal-2022-korean,
title = "{K}orean Language Modeling via Syntactic Guide",
author = "Kim, Hyeondey and
Kim, Seonhoon and
Kang, Inho and
Kwak, Nojun and
Fung, Pascale",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.304",
pages = "2841--2849",
abstract = "While pre-trained language models play a vital role in modern language processing tasks, but not every language can benefit from them. Most existing research on pre-trained language models focuses primarily on widely-used languages such as English, Chinese, and Indo-European languages. Additionally, such schemes usually require extensive computational resources alongside a large amount of data, which is infeasible for less-widely used languages. We aim to address this research niche by building a language model that understands the linguistic phenomena in the target language which can be trained with low-resources. In this paper, we discuss Korean language modeling, specifically methods for language representation and pre-training methods. With our Korean-specific language representation, we are able to build more powerful language models for Korean understanding, even with fewer resources. The paper proposes chunk-wise reconstruction of the Korean language based on a widely used transformer architecture and bidirectional language representation. We also introduce morphological features such as Part-of-Speech (PoS) into the language understanding by leveraging such information during the pre-training. Our experiment results prove that the proposed methods improve the model performance of the investigated Korean language understanding tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-korean">
<titleInfo>
<title>Korean Language Modeling via Syntactic Guide</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyeondey</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonhoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inho</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nojun</namePart>
<namePart type="family">Kwak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>While pre-trained language models play a vital role in modern language processing tasks, but not every language can benefit from them. Most existing research on pre-trained language models focuses primarily on widely-used languages such as English, Chinese, and Indo-European languages. Additionally, such schemes usually require extensive computational resources alongside a large amount of data, which is infeasible for less-widely used languages. We aim to address this research niche by building a language model that understands the linguistic phenomena in the target language which can be trained with low-resources. In this paper, we discuss Korean language modeling, specifically methods for language representation and pre-training methods. With our Korean-specific language representation, we are able to build more powerful language models for Korean understanding, even with fewer resources. The paper proposes chunk-wise reconstruction of the Korean language based on a widely used transformer architecture and bidirectional language representation. We also introduce morphological features such as Part-of-Speech (PoS) into the language understanding by leveraging such information during the pre-training. Our experiment results prove that the proposed methods improve the model performance of the investigated Korean language understanding tasks.</abstract>
<identifier type="citekey">kim-etal-2022-korean</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.304</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2841</start>
<end>2849</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Korean Language Modeling via Syntactic Guide
%A Kim, Hyeondey
%A Kim, Seonhoon
%A Kang, Inho
%A Kwak, Nojun
%A Fung, Pascale
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F kim-etal-2022-korean
%X While pre-trained language models play a vital role in modern language processing tasks, but not every language can benefit from them. Most existing research on pre-trained language models focuses primarily on widely-used languages such as English, Chinese, and Indo-European languages. Additionally, such schemes usually require extensive computational resources alongside a large amount of data, which is infeasible for less-widely used languages. We aim to address this research niche by building a language model that understands the linguistic phenomena in the target language which can be trained with low-resources. In this paper, we discuss Korean language modeling, specifically methods for language representation and pre-training methods. With our Korean-specific language representation, we are able to build more powerful language models for Korean understanding, even with fewer resources. The paper proposes chunk-wise reconstruction of the Korean language based on a widely used transformer architecture and bidirectional language representation. We also introduce morphological features such as Part-of-Speech (PoS) into the language understanding by leveraging such information during the pre-training. Our experiment results prove that the proposed methods improve the model performance of the investigated Korean language understanding tasks.
%U https://aclanthology.org/2022.lrec-1.304
%P 2841-2849
Markdown (Informal)
[Korean Language Modeling via Syntactic Guide](https://aclanthology.org/2022.lrec-1.304) (Kim et al., LREC 2022)
ACL
- Hyeondey Kim, Seonhoon Kim, Inho Kang, Nojun Kwak, and Pascale Fung. 2022. Korean Language Modeling via Syntactic Guide. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2841–2849, Marseille, France. European Language Resources Association.