@inproceedings{kim-etal-2026-script,
title = "{SCRIPT}: A Subcharacter Compositional Representation Injection Module for {K}orean Pre-Trained Language Models",
author = "Kim, SungHo and
Park, Juhyeong and
Atalay, Eda and
Lee, SangKeun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.104/",
pages = "2185--2213",
ISBN = "979-8-89176-395-1",
abstract = "Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure of Korean but also encode frequent and linguistically meaningful morphophonological processes. However, most current Korean language models (LMs) are based on subword tokenization schemes, which are not explicitly designed to capture the internal compositional structure of characters. To address this limitation, we propose $\textbf{SCRIPT}$, a model-agnostic module that injects subcharacter compositional knowledge into Korean PLMs.$\textbf{SCRIPT}$ allows to enhance subword embeddings with structural granularity, without requiring architectural changes or additional pre-training.As a result, $\textbf{SCRIPT}$ consistently enhances all baselines across various Korean natural language understanding (NLU) and generation (NLG) tasks. Moreover, beyond performance gains, detailed linguistic analyses show that $\textbf{SCRIPT}$ reshapes the embedding space in a way that better captures grammatical regularities and semantically cohesive variations. Our code is available at [https://github.com/SungHo3268/SCRIPT](https://github.com/SungHo3268/SCRIPT)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-script">
<titleInfo>
<title>SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">SungHo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juhyeong</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eda</namePart>
<namePart type="family">Atalay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SangKeun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure of Korean but also encode frequent and linguistically meaningful morphophonological processes. However, most current Korean language models (LMs) are based on subword tokenization schemes, which are not explicitly designed to capture the internal compositional structure of characters. To address this limitation, we propose SCRIPT, a model-agnostic module that injects subcharacter compositional knowledge into Korean PLMs.SCRIPT allows to enhance subword embeddings with structural granularity, without requiring architectural changes or additional pre-training.As a result, SCRIPT consistently enhances all baselines across various Korean natural language understanding (NLU) and generation (NLG) tasks. Moreover, beyond performance gains, detailed linguistic analyses show that SCRIPT reshapes the embedding space in a way that better captures grammatical regularities and semantically cohesive variations. Our code is available at [https://github.com/SungHo3268/SCRIPT](https://github.com/SungHo3268/SCRIPT).</abstract>
<identifier type="citekey">kim-etal-2026-script</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.104/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2185</start>
<end>2213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models
%A Kim, SungHo
%A Park, Juhyeong
%A Atalay, Eda
%A Lee, SangKeun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F kim-etal-2026-script
%X Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure of Korean but also encode frequent and linguistically meaningful morphophonological processes. However, most current Korean language models (LMs) are based on subword tokenization schemes, which are not explicitly designed to capture the internal compositional structure of characters. To address this limitation, we propose SCRIPT, a model-agnostic module that injects subcharacter compositional knowledge into Korean PLMs.SCRIPT allows to enhance subword embeddings with structural granularity, without requiring architectural changes or additional pre-training.As a result, SCRIPT consistently enhances all baselines across various Korean natural language understanding (NLU) and generation (NLG) tasks. Moreover, beyond performance gains, detailed linguistic analyses show that SCRIPT reshapes the embedding space in a way that better captures grammatical regularities and semantically cohesive variations. Our code is available at [https://github.com/SungHo3268/SCRIPT](https://github.com/SungHo3268/SCRIPT).
%U https://aclanthology.org/2026.findings-acl.104/
%P 2185-2213
Markdown (Informal)
[SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models](https://aclanthology.org/2026.findings-acl.104/) (Kim et al., Findings 2026)
ACL